@misc{kong2025world3d4d, title = {3D and 4D World Modeling: A Survey}, author = {Lingdong Kong and Yu Yang and Jianbiao Mei and Youquan Liu and Ao Liang and Dekai Zhu and Dongyue Lu and Wei Yin and Xiaotao Hu and Mingkai Jia and Junyuan Deng and Kaiwen Zhang and Yang Wu and Tianyi Yan and Shenyuan Gao and Song Wang and Linfeng Li and Liang Pan and Yong Liu and Jianke Zhu and Wei Tsang Ooi and Steven C. H. Hoi and Ziwei Liu}, year = {2025}, eprint = {2509.07996}, archiveprefix = {arXiv} } @misc{worldmodelroadmap2026, title = {A Definition and Roadmap for World Models}, author = {Xinyuan Chen and Haoyu Guo and Shi Guo and Bingqi Jiang and Chunhua Shen and Xing Shen and Tianfan Xue and Yufei Xue and Mulin Yu and Weinan Zhang and Bin Zhao and Bowen Zhou and Ming Zhou}, year = {2026}, eprint = {2607.06401}, archiveprefix = {arXiv} } @inproceedings{wildworld2026, title = {A Large-Scale Game Video Dataset with Action and State Annotations}, author = {Li, Zhen and Meng, Zian and Shi, Shuwei and Peng, Wenshuo and Zheng, Bo and Jia, Yunde and Wu, Yuwei and Li, Chuanhao and Zhang, Kaipeng}, booktitle = {Computer Vision -- ECCV 2026}, year = {2026}, volume = {17064}, pages = {571--588}, doi = {10.1007/978-3-032-37196-6_31}, } @inproceedings{feichtenhofer2021large, title = {A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning}, author = {Feichtenhofer, Christoph and Fan, Haoqi and Xiong, Bo and Girshick, Ross and He, Kaiming}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, pages = {3299--3309}, doi = {10.1109/cvpr46437.2021.00331} } @inproceedings{prajwal2020wav2lip, title = {A Lip Sync Expert Is All You Need for Speech to Lip Generation in the Wild}, author = {Prajwal, K R and Mukhopadhyay, Rudrabha and Namboodiri, Vinay P. and Jawahar, C.V.}, booktitle = {Proceedings of the ACM International Conference on Multimedia}, year = {2020}, pages = {484--492}, doi = {10.1145/3394171.3413532} } @inproceedings{xu2026mapa, title = {A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning}, author = {Xu, Yichang and Liu, Gaowen and Kompella, Ramana Rao and Huang, Tiansheng and Hu, Sihao and Ilhan, Fatih and Tekin, Selim Furkan and Yahn, Zachary and Liu, Ling}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {19497--19507}, } @inproceedings{barratt2018inception, title = {A Note on the Inception Score}, author = {Shane Barratt and Rishi Sharma}, booktitle = {ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models}, year = {2018} } @misc{lecun2022path, title = {A Path Towards Autonomous Machine Intelligence}, author = {Yann LeCun}, year = {2022}, } @article{krojer2025mvp, title = {A Shortcut-Aware Video-{QA} Benchmark for Physical Understanding via Minimal Video Pairs}, author = {Benno Krojer and Mojtaba Komeili and Candace Ross and Quentin Garrido and Koustuv Sinha and Nicolas Ballas and Mido Assran}, journal = {Transactions on Machine Learning Research}, year = {2025}, issn = {2835-8856} } @misc{li2024survey, title = {A Survey on Long Video Generation: Challenges, Methods, and Prospects}, author = {Li, Chengxuan and Huang, Di and Lu, Zeyu and Xiao, Yang and Pei, Qingqi and Bai, Lei}, year = {2024}, eprint = {2403.16407}, archiveprefix = {arXiv} } @article{yin2023mllmsurvey, title = {A Survey on Multimodal Large Language Models}, author = {Yin, Shukang and Fu, Chaoyou and Zhao, Sirui and Li, Ke and Sun, Xing and Xu, Tong and Chen, Enhong}, journal = {National Science Review}, year = {2024}, volume = {11}, number = {12}, eid = {nwae403}, doi = {10.1093/nsr/nwae403} } @article{xing2023videodiffusionsurvey, title = {A Survey on Video Diffusion Models}, author = {Xing, Zhen and Feng, Qijun and Chen, Haoran and Dai, Qi and Hu, Han and Xu, Hang and Wu, Zuxuan and Jiang, Yu-Gang}, journal = {ACM Computing Surveys}, year = {2025}, volume = {57}, number = {2}, pages = {1--42}, doi = {10.1145/3696415} } @misc{alhamidi2026repair, title = {Accuracy and Cost Claims Do Not Survive Re-Execution in Agentic VideoQA}, author = {Rama AlHamidi and Aseel Mohamed and Rasul Khanbayov and Mohamed Rayan Barhdadi and Erchin Serpedin and Hasan Kurban}, year = {2026}, eprint = {2607.01469}, archiveprefix = {arXiv} } @misc{arai2024actbench, title = {ACT-Bench: Towards Action Controllable World Models for Autonomous Driving}, author = {Hidehisa Arai and Keishi Ishihara and Tsubasa Takahashi and Yu Yamaguchi}, year = {2024}, eprint = {2412.05337}, archiveprefix = {arXiv} } @misc{sundar2026actionforcing, title = {Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases}, author = {Ashish Sundar and Tiankuo Hou and Zhong Fan and Chunbo Luo and Xiaoyang Wang}, year = {2026}, eprint = {2609.30595}, archiveprefix = {arXiv} } @misc{chen2026action100m, title = {Action100M: A Large-Scale Video Action Dataset}, author = {Delong Chen and Tejaswi Kasarla and Yejin Bang and Mustafa Shukor and Willy Chung and Jade Yu and Allen Bolourchi and Theo Moutakanni and Pascale Fung}, year = {2026}, eprint = {2601.10592}, archiveprefix = {arXiv} } @inproceedings{yu2019activitynet, title = {ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering}, author = {Yu, Zhou and Xu, Dejing and Yu, Jun and Yu, Ting and Zhao, Zhou and Zhuang, Yueting and Tao, Dacheng}, booktitle = {Proceedings of the AAAI conference on artificial intelligence}, year = {2019}, pages = {9127--9134}, doi = {10.1609/aaai.v33i01.33019127} } @inproceedings{caba2015activitynet, title = {ActivityNet: A Large-Scale Video Benchmark for Human Activity Understanding}, author = {Heilbron, Fabian Caba and Escorcia, Victor and Ghanem, Bernard and Niebles, Juan Carlos}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2015}, pages = {961--970}, doi = {10.1109/cvpr.2015.7298698} } @inproceedings{gao2025adaworld, title = {{AdaWorld}: Learning Adaptable World Models with Latent Actions}, author = {Gao, Shenyuan and Zhou, Siyuan and Du, Yilun and Zhang, Jun and Gan, Chuang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {18744--18771}, } @inproceedings{zhang2023adding, title = {Adding Conditional Control to Text-to-Image Diffusion Models}, author = {Zhang, Lvmin and Rao, Anyi and Agrawala, Maneesh}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {3836--3847}, doi = {10.1109/iccv51070.2023.00355} } @misc{wu2026worldtrace, title = {Addressable Memory for Video World Models}, author = {Xindi Wu and Sven Elflein and James Lucas and Olga Russakovsky and Laura Leal-Taixé and Despoina Paschalidou and Jonathan Lorraine and Aljoša Ošep}, year = {2026}, eprint = {2608.07408}, archiveprefix = {arXiv} } @inproceedings{xue2022hdvila, title = {Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions}, author = {Xue, Hongwei and Hang, Tiankai and Zeng, Yanhong and Sun, Yuchong and Liu, Bei and Yang, Huan and Fu, Jianlong and Guo, Baining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {5036--5045}, doi = {10.1109/cvpr52688.2022.00498} } @misc{alradi2026aeroworld, title = {Aero-World: Action-Conditioned Aerial Video Generation from Inertial Controls}, author = {Abdul Mohaimen Al Radi and Kunyang Li and Yuzhang Shang and Mubarak Shah and Yu Tian}, year = {2026}, eprint = {2605.19728}, archiveprefix = {arXiv} } @misc{an2026agentvidbench, title = {{AgentVidBench}: A Multi-Hop Video Question Answering Benchmark for Evaluating {MLLM} Agents}, author = {Seoyeon An and Hyeonseo Jang and Minsu Kim and Chanho Lee and Younghan Park and Kangwook Lee}, year = {2026}, eprint = {2609.21386}, archiveprefix = {arXiv} } @misc{luo2026ai, title = {{AI} for Games in the Foundation Model Era}, author = {Luo, Meng and Li, Yanlin and Li, Hao and Lin, Hongzhan and Zhou, Pengfei and Ju, Tianjie and Zhang, Ran and Jin, Yeying and Lee, Mong-Li and Hsu, Wynne}, year = {2026}, eprint = {2609.16679}, archiveprefix = {arXiv} } @inproceedings{blattmann2023videoldm, title = {Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models}, author = {Blattmann, Andreas and Rombach, Robin and Ling, Huan and Dockhorn, Tim and Kim, Seung Wook and Fidler, Sanja and Kreis, Karsten}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {22563--22575}, doi = {10.1109/cvpr52729.2023.02161} } @inproceedings{dosovitskiyimage, title = {An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale}, author = {Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2021} } @inproceedings{gal2022textualinversion, title = {An Image Is Worth One Word: Personalizing Text-to-Image Generation Using Textual Inversion}, author = {Rinon Gal and Yuval Alaluf and Yuval Atzmon and Or Patashnik and Amit H. Bermano and Gal Chechik and Daniel Cohen-Or}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{anchorweave2026, title = {AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories}, author = {Wang, Zun and Lin, Han and Yoon, Jaehong and Cho, Jaemin and Zhang, Yue and Bansal, Mohit}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {203--224}, doi = {10.1007/978-3-032-37356-4_12} } @inproceedings{li2024animdirector, title = {{Anim-Director}: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation}, author = {Li, Yunxin and Shi, Haoyuan and Hu, Baotian and Wang, Longyue and Zhu, Jiashun and Xu, Jinyi and Zhao, Zhen and Zhang, Min}, booktitle = {SIGGRAPH Asia 2024 Conference Papers}, year = {2024}, pages = {1--11}, doi = {10.1145/3680528.3687688} } @inproceedings{hu2024animate, title = {Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation}, author = {Hu, Li}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {8153--8163}, doi = {10.1109/cvpr52733.2024.00779} } @inproceedings{guo2024animatediff, title = {AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models Without Specific Tuning}, author = {Guo, Yuwei and Yang, Ceyuan and Rao, Anyi and Liang, Zhengyang and Wang, Yaohui and Qiao, Yu and Agrawala, Maneesh and Lin, Dahua and Dai, Bo}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @misc{wu2025any2caption, title = {Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation}, author = {Shengqiong Wu and Weicai Ye and Jiahao Wang and Quande Liu and Xintao Wang and Pengfei Wan and Di Zhang and Kun Gai and Shuicheng Yan and Hao Fei and Tat-Seng Chua}, year = {2025}, eprint = {2503.24379}, archiveprefix = {arXiv} } @misc{huang2026apmbench, title = {{APM-Bench}: Benchmarking Cross-Session Persistent Memory for Egocentric Streaming Video Assistants}, author = {Jianguo Huang and Jinming Liu and Qiyao Wang and Liang Xu and Jianhang Li and Zhimian Wen and Mingda Li and Shule Lu and Zhicheng Wang and Yuhan Guo and Xin Jin and Wenjun Zeng}, year = {2026}, eprint = {2609.37559}, archiveprefix = {arXiv} } @inproceedings{zohar2025apollo, title = {Apollo: An Exploration of Video Understanding in Large Multimodal Models}, author = {Zohar, Orr and Wang, Xiaohan and Dubois, Yann and Mehta, Nikhil and Xiao, Tong and Hansen-Estruch, Philippe and Yu, Licheng and Wang, Xiaofang and Juefei-Xu, Felix and Zhang, Ning and Yeung-Levy, Serena and Xia, Xide}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {18891--18901}, doi = {10.1109/cvpr52734.2025.01760} } @misc{wu2026apt, title = {APT: Atomic Physical Transitions for Causal Video-Language Understanding}, author = {Shang Wu and Haoran Lu and Songling Liu and Chenwei Xu and Lie Lu and Pranav Maneriker and Fan Du and Zhaoran Wang and Han Liu}, year = {2026}, eprint = {2606.18586}, archiveprefix = {arXiv} } @misc{zhang2026arcbench, title = {ARC-Bench: Closed-Loop Replanning Masks Broken Action Ranking in Frozen JEPA World Models}, author = {Zhengshu Zhang and Zhiyuan Li}, year = {2026}, eprint = {2609.05461}, archiveprefix = {arXiv} } @inproceedings{rawal2025argus, title = {ARGUS: Hallucination and Omission Evaluation in Video-LLMs}, author = {Rawal, Ruchit and Shirkavand, Reza and Huang, Heng and Somepalli, Gowthami and Goldstein, Tom}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {20280--20290}, doi = {10.1109/iccv51701.2025.01886} } @inproceedings{yang2021aot, title = {Associating Objects with Transformers for Video Object Segmentation}, author = {Yang, Zongxin and Wei, Yunchao and Yang, Yi}, booktitle = {Advances in Neural Information Processing Systems}, year = {2021}, volume = {34} } @inproceedings{lu2025atoken, title = {AToken: A Unified Tokenizer for Vision}, author = {Lu, Jiasen and Song, Liangchen and Xu, Mingze and Ahn, Byeongjoo and Wang, Yanjun and Chen, Chen and Dehghan, Afshin and Yang, Yinfei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {28701--28711}, } @inproceedings{vaswani2017attention, title = {Attention Is All You Need}, author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia}, booktitle = {Advances in Neural Information Processing Systems}, year = {2017}, volume = {30}, } @inproceedings{audioset2017, title = {Audio Set: An Ontology and Human-Labeled Dataset for Audio Events}, author = {Gemmeke, Jort F. and Ellis, Daniel P. W. and Freedman, Dylan and Jansen, Aren and Lawrence, Wade and Moore, R. Channing and Plakal, Manoj and Ritter, Marvin}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year = {2017}, pages = {776--780}, doi = {10.1109/icassp.2017.7952261} } @inproceedings{ave2018, title = {Audio-Visual Event Localization in Unconstrained Videos}, author = {Tian, Yapeng and Shi, Jing and Li, Bochen and Duan, Zhiyao and Xu, Chenliang}, booktitle = {European Conference on Computer Vision (ECCV)}, year = {2018}, pages = {252--268}, doi = {10.1007/978-3-030-01216-8_16} } @misc{qin2026audiovisual, title = {Audio-Visual Intelligence in Large Foundation Models}, author = {You Qin and Kai Liu and Shengqiong Wu and Kai Wang and Shijian Deng and Yapeng Tian and Junbin Xiao and Yazhou Xing and Yinghao Ma and Bobo Li and Roger Zimmermann and Lei Cui and Furu Wei and Jiebo Luo and Hao Fei}, year = {2026}, eprint = {2605.04045}, archiveprefix = {arXiv} } @inproceedings{kingma2013auto, title = {Auto-Encoding Variational Bayes}, author = {Kingma, Diederik P and Welling, Max}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2014} } @misc{wu2025movieagent, title = {Automated Movie Generation via Multi-Agent CoT Planning}, author = {Weijia Wu and Zeyu Zhu and Mike Zheng Shou}, year = {2025}, eprint = {2503.07314}, archiveprefix = {arXiv} } @inproceedings{lin2025aapt, title = {Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation}, author = {Lin, Shanchuan and Yang, Ceyuan and He, Hao and Jiang, Jianwen and Ren, Yuxi and Xia, Xin and Zhao, Yang and Xiao, Xuefeng and Jiang, Lu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {41061--41086}, doi = {10.52202/085713-1371} } @inproceedings{lee2022rqvae, title = {Autoregressive Image Generation Using Residual Quantization}, author = {Lee, Doyup and Kim, Chiheon and Kim, Saehoon and Cho, Minsu and Han, Wook-Shin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {11523--11532}, doi = {10.1109/cvpr52688.2022.01123} } @inproceedings{li2024mar, title = {Autoregressive Image Generation Without Vector Quantization}, author = {Li, Tianhong and Tian, Yonglong and Li, He and Deng, Mingyang and He, Kaiming}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {56424--56445}, doi = {10.52202/079017-1797} } @inproceedings{deng2024nova, title = {Autoregressive Video Generation Without Vector Quantization}, author = {Deng, Haoge and Pan, Ting and Diao, Haiwen and Luo, Zhengxiong and Cui, Yufeng and Lu, Huchuan and Shan, Shiguang and Qi, Yonggang and Wang, Xinlong}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{zhang2025avila, title = {AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction}, author = {Gengyuan Zhang and Tanveer Hannan and Hermine Kleiner and Beste Aydemir and Xinyu Xie and Jian Lan and Thomas Seidl and Volker Tresp and Jindong Gu}, year = {2025}, eprint = {2506.18472}, archiveprefix = {arXiv} } @inproceedings{yu2020bdd100k, title = {BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning}, author = {Yu, Fisher and Chen, Haofeng and Wang, Xin and Xian, Wenqi and Chen, Yingying and Liu, Fangchen and Madhavan, Vashisht and Darrell, Trevor}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, pages = {2633--2642}, doi = {10.1109/cvpr42600.2020.00271} } @inproceedings{hu2025videoscience, title = {Benchmarking Scientific Understanding and Reasoning for Video Generation Using VideoScience-Bench}, author = {Hu, Lanxiang and Shankarampeta, Abhilash and Huang, Yixin and Dai, Zilin and Yu, Haoyang and Zhao, Yujie and Kang, Haoqiang and Zhao, Daniel and Rosing, Tajana and Zhang, Hao}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {151--168}, doi = {10.1007/978-3-032-37624-4_9} } @inproceedings{luo2024jedi, title = {Beyond {FVD}: An Enhanced Metric for Evaluating Video Generation Distribution Quality}, author = {Luo, Ge Ya and Favero, Gian Mario and Luo, Zhi Hao and Jolicoeur-Martineau, Alexia and Pal, Christopher}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{tong2026multimodalpretraining, title = {Beyond Language Modeling: An Exploration of Multimodal Pretraining}, author = {Tong, Shengbang and Fan, David and Nguyen, John and Brown, Ellis and Zhou, Gaoyue and Qian, Shengyi and Zheng, Boyang and Vallaeys, Th\'{e}ophane and Fergus, Rob and Murray, Naila and Ghazvininejad, Marjan and Lewis, Mike and Ballas, Nicolas and Bar, Amir and Rabbat, Michael and Verbeek, Jakob and Zettlemoyer, Luke and Sinha, Koustuv and LeCun, Yann and Xie, Saining}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {121519--121546}, } @misc{rui2026biwm, title = {BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression}, author = {Shaohao Rui and Xiaofeng Mao and Zhanyu Zhang and Peijia Lin and Yansong Zhu and Yibo Zhang and Haibin Wan and Zhangrui Zhao and Weijie Ma}, year = {2026}, eprint = {2606.10135}, archiveprefix = {arXiv} } @inproceedings{pmlr-v202-li23q, title = {{BLIP}-2: Bootstrapping Language-Image Pre-Training with Frozen Image Encoders and Large Language Models}, author = {Li, Junnan and Li, Dongxu and Savarese, Silvio and Hoi, Steven}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, year = {2023}, volume = {202}, pages = {19730--19742}, } @misc{vega2026, title = {Bridging Video Understanding and Generation in a Unified Framework}, author = {Yuqi Wang and Runyi Li and Ruoyu Feng and Renjie Chen and Wenfeng Lin and Mingyu Guo}, year = {2026}, eprint = {2606.31326}, archiveprefix = {arXiv} } @article{sadeghi2026calibench, title = {CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?}, author = {Jonathan Sadeghi and Jenny Seidenschwarz and Jesse Allardice and Sirish Srinivasan and Benjamin Graham and Jeffrey Hawke}, journal = {Transactions on Machine Learning Research}, year = {2026}, issn = {2835-8856} } @inproceedings{he2024cameractrl, title = {{CameraCtrl: Enabling Camera Control for Video Diffusion Models}}, author = {Hao He and Yinghao Xu and Yuwei Guo and Gordon Wetzstein and Bo Dai and Hongsheng Li and Ceyuan Yang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{du2026case, title = {CASE: Cost-Aware Stopping for Efficient Long-Video Agents}, author = {Yiming Du and Chenghao Liu and Zhiyuan Liu and Fangxing Zheng and Zhao Wang and Junnan Nie and Songfang Huang}, year = {2026}, eprint = {2610.05400}, archiveprefix = {arXiv} } @inproceedings{zhang2026castbench, title = {CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering}, author = {Zhang, Mingfang and Pan, Jingjing and Kumar, Ashutosh and Saini, Rajat and Erdogan, Mustafa and Yang, Hsuan-Kung and Kang, Caixin and Huang, Yifei and Sato, Yoichi and Kong, Quan}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {31856--31866}, } @misc{zhao2026causalforcingpp, title = {Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation}, author = {Zhao, Min and Zhu, Hongzhou and Zheng, Kaiwen and Zhou, Zihan and Yan, Bokai and Li, Xinyuan and Yang, Xiao and Li, Chongxuan and Zhu, Jun}, year = {2026}, eprint = {2605.15141}, archiveprefix = {arXiv} } @inproceedings{zhu2026causalforcing, title = {Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation}, author = {Zhu, Hongzhou and Zhao, Min and He, Guande and Su, Hang and Li, Chongxuan and Zhu, Jun}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {168030--168049}, } @inproceedings{causaljepa2026, title = {Causal-{JEPA}: Learning World Models Through Object-Level Latent Masking}, author = {Nam, Heejeong and Le Lidec, Quentin and Maes, Lucas and LeCun, Yann and Balestriero, Randall}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {91808--91832}, } @misc{foss2025causalvqa, title = {CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models}, author = {Aaron Foss and Chloe Evans and Sasha Mitts and Koustuv Sinha and Ammar Rizvi and Justine T. Kao}, year = {2025}, eprint = {2506.09943}, archiveprefix = {arXiv} } @misc{cgworld2026, title = {CG-World: A Large-Scale World-State Dataset and Protocol for World Models}, author = {Yiming Cai and Fangjie Yu and Meiqing Yu and Ziyue Shi and Pengfei Yuan and Yong Guo}, year = {2026}, eprint = {2607.26452}, archiveprefix = {arXiv} } @misc{team2024chameleon, title = {Chameleon: Mixed-Modal Early-Fusion Foundation Models}, author = {Chameleon Team}, year = {2024}, eprint = {2405.09818}, archiveprefix = {arXiv} } @inproceedings{jin2023chatunivi, title = {Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding}, author = {Jin, Peng and Takanobu, Ryuichi and Zhang, Wancai and Cao, Xiaochun and Yuan, Li}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {13700--13710}, doi = {10.1109/cvpr52733.2024.01300} } @inproceedings{yuan2024chronomagicbenchbenchmarkmetamorphicevaluation, title = {ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-Lapse Video Generation}, author = {Yuan, Shenghai and Huang, Jinfa and Xu, Yongqi and Liu, Yaoyang and Zhang, Shaofeng and Shi, Yujun and Zhu, Ruijie and Cheng, Xinhua and Luo, Jiebo and Yuan, Li}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {21236--21270}, doi = {10.52202/079017-0669} } @misc{ho2022classifierfree, title = {Classifier-Free Diffusion Guidance}, author = {Jonathan Ho and Tim Salimans}, year = {2022}, eprint = {2207.12598}, archiveprefix = {arXiv}, } @inproceedings{clevrer2019, title = {CLEVRER: Collision Events for Video Representation and Reasoning}, author = {Kexin Yi and Chuang Gan and Yunzhu Li and Pushmeet Kohli and Jiajun Wu and Antonio Torralba and Joshua B. Tenenbaum}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2020} } @article{luo2022clip4clip, title = {CLIP4Clip: An Empirical Study of CLIP for End to End Video CLIP Retrieval and Captioning}, author = {Luo, Huaishao and Ji, Lei and Zhong, Ming and Chen, Yang and Lei, Wen and Duan, Nan and Li, Tianrui}, journal = {Neurocomputing}, year = {2022}, volume = {508}, pages = {293--304}, doi = {10.1016/j.neucom.2022.07.028} } @inproceedings{hessel2022clipscorereferencefreeevaluationmetric, title = {CLIPScore: A Reference-Free Evaluation Metric for Image Captioning}, author = {Hessel, Jack and Holtzman, Ari and Forbes, Maxwell and Le Bras, Ronan and Choi, Yejin}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, year = {2021}, pages = {7514--7528}, doi = {10.18653/v1/2021.emnlp-main.595} } @inproceedings{hongcogvideo, title = {CogVideo: Large-Scale Pretraining for Text-to-Video Generation via Transformers}, author = {Hong, Wenyi and Ding, Ming and Zheng, Wendi and Liu, Xinghan and Tang, Jie}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{yang2024cogvideox, title = {CogVideoX: Text-to-Video Diffusion Models with an Expert Transformer}, author = {Yang, Zhuoyi and Teng, Jiayan and Zheng, Wendi and Ding, Ming and Huang, Shiyu and Xu, Jiazheng and Yang, Yuanming and Hong, Wenyi and Zhang, Xiaohan and Feng, Guanyu and Yin, Da and Zhang, Yuxuan and Wang, Weihan and Cheng, Yean and Xu, Bin and Gu, Xiaotao and Dong, Yuxiao and Tang, Jie}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{tang2019coin, title = {COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysis}, author = {Tang, Yansong and Ding, Dajun and Rao, Yongming and Zheng, Yu and Zhang, Danyang and Zhao, Lili and Lu, Jiwen and Zhou, Jie}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2019}, pages = {1207--1216}, doi = {10.1109/cvpr.2019.00130} } @inproceedings{yu2025contextmemory, title = {Context As Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval}, author = {Yu, Jiwen and Bai, Jianhong and Qin, Yiran and Liu, Quande and Wang, Xintao and Wan, Pengfei and Zhang, Di and Liu, Xihui}, booktitle = {Proceedings of the SIGGRAPH Asia 2025 Conference Papers}, year = {2025}, pages = {1--11}, doi = {10.1145/3757377.3763833} } @inproceedings{gao2025loraedit, title = {Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning}, author = {Gao, Chenjian and Ding, Lihe and Cai, Xin and Huang, Zhanpeng and Wang, Zibin and Xue, Tianfan}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{cosmos3_2026, title = {Cosmos 3: Omnimodal World Models for Physical AI}, author = {{NVIDIA}}, year = {2026}, eprint = {2606.02800}, archiveprefix = {arXiv} } @misc{nvidia2025cosmos, title = {Cosmos World Foundation Model Platform for Physical AI}, author = {{NVIDIA} and Niket Agarwal and Arslan Ali and Maciej Bala and Yogesh Balaji and Erik Barker and Tiffany Cai and Prithvijit Chattopadhyay and Yongxin Chen and Yin Cui and Yifan Ding and Daniel Dworakowski and Jiaojiao Fan and Michele Fenzi and Francesco Ferroni and Sanja Fidler and Dieter Fox and Songwei Ge and Yunhao Ge and Jinwei Gu and Siddharth Gururani and Ethan He and Jiahui Huang and Jacob Huffman and Pooya Jannaty and Jingyi Jin and Seung Wook Kim and Gergely Klár and Grace Lam and Shiyi Lan and Laura Leal-Taixe and Anqi Li and Zhaoshuo Li and Chen-Hsuan Lin and Tsung-Yi Lin and Huan Ling and Ming-Yu Liu and Xian Liu and Alice Luo and Qianli Ma and Hanzi Mao and Kaichun Mo and Arsalan Mousavian and Seungjun Nah and Sriharsha Niverty and David Page and Despoina Paschalidou and Zeeshan Patel and Lindsey Pavao and Morteza Ramezanali and Fitsum Reda and Xiaowei Ren and Vasanth Rao Naik Sabavat and Ed Schmerling and Stella Shi and Bartosz Stefaniak and Shitao Tang and Lyne Tchapmi and Przemek Tredak and Wei-Cheng Tseng and Jibin Varghese and Hao Wang and Haoxiang Wang and Heng Wang and Ting-Chun Wang and Fangyin Wei and Xinyue Wei and Jay Zhangjie Wu and Jiashu Xu and Wei Yang and Lin Yen-Chen and Xiaohui Zeng and Yu Zeng and Jing Zhang and Qinsheng Zhang and Yuxuan Zhang and Qingqing Zhao and Artur Zolkowski}, year = {2025}, eprint = {2501.03575}, archiveprefix = {arXiv} } @misc{cosmosdrivedreams2025, title = {Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models}, author = {Xuanchi Ren and Yifan Lu and Tianshi Cao and Ruiyuan Gao and Shengyu Huang and Amirmojtaba Sabour and Tianchang Shen and Tobias Pfaff and Jay Zhangjie Wu and Runjian Chen and Seung Wook Kim and Jun Gao and Laura Leal-Taixe and Mike Chen and Sanja Fidler and Huan Ling}, year = {2025}, eprint = {2506.09042}, archiveprefix = {arXiv} } @misc{poppi2026countervid, title = {{CounterVid}: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models}, author = {Tobia Poppi and Burak Uzkent and Amanmeet Garg and Lucas Porto and Garin Kessler and Yezhou Yang and Marcella Cornia and Lorenzo Baraldi and Rita Cucchiara and Florian Schiffers}, year = {2026}, eprint = {2601.04778}, archiveprefix = {arXiv} } @misc{cronos2026, title = {CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models}, author = {León Begiristain and Olaf Dünkel and Adam Kortylewski}, year = {2026}, eprint = {2605.23699}, archiveprefix = {arXiv} } @inproceedings{zhukov2019crosstask, title = {Cross-Task Weakly Supervised Learning from Instructional Videos}, author = {Zhukov, Dimitri and Alayrac, Jean-Baptiste and Cinbis, Ramazan Gokberk and Fouhey, David and Laptev, Ivan and Sivic, Josef}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2019}, pages = {3532--3540}, doi = {10.1109/cvpr.2019.00365} } @inproceedings{guo2025ctrlworld, title = {Ctrl-World: A Controllable Generative World Model for Robot Manipulation}, author = {Guo, Yanjiang and Shi, Lucy Xiaoyang and Chen, Jianyu and Finn, Chelsea}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{zhao2024cvvae, title = {CV-VAE: A Compatible Video VAE for Latent Generative Video Models}, author = {Zhao, Sijie and Zhang, Yong and Cun, Xiaodong and Yang, Shaoshu and Niu, Muyao and Li, Xiaoyu and Hu, Wenbo and Shan, Ying}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {12847--12871}, doi = {10.52202/079017-0409} } @misc{shan2026cyclegen, title = {CyCLeGen: Cycle-Consistent Layout Prediction and Image Generation in Vision Foundation Models}, author = {Xiaojun Shan and Haoyu Shen and Yucheng Mao and Xiang Zhang and Abhay Anand and Bingnan Li and Haiyang Xu and Zhuowen Tu}, year = {2026}, eprint = {2603.14957}, archiveprefix = {arXiv} } @inproceedings{sohl2015deep, title = {Deep Unsupervised Learning Using Nonequilibrium Thermodynamics}, author = {Jascha Sohl-Dickstein and Eric A. Weiss and Niru Maheswaranathan and Surya Ganguli}, booktitle = {Proceedings of the 32nd International Conference on Machine Learning}, year = {2015}, volume = {37}, pages = {2256--2265}, organization = {pmlr} } @inproceedings{zhang2025deepvideodiscovery, title = {Deep Video Discovery: Agentic Search with Tool Use for Long-Form Video Understanding}, author = {Zhang, Xiaoyi and Jia, Zhaoyang and Guo, Zongyu and Li, Jiahao and Li, Bin and Li, Houqiang and Lu, Yan}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {89863--89895}, doi = {10.52202/085713-3005} } @article{guo2025deepseek, title = {DeepSeek-R1 Incentivizes Reasoning in LLMs Through Reinforcement Learning}, author = {Guo, Daya and Yang, Dejian and Zhang, Haowei and Song, Junxiao and Wang, Peiyi and Zhu, Qihao and Xu, Runxin and Zhang, Ruoyu and Ma, Shirong and Bi, Xiao and Zhang, Xiaokang and Yu, Xingkai and Wu, Yu and Wu, Z. F. and Gou, Zhibin and Shao, Zhihong and Li, Zhuoshu and Gao, Ziyi and Liu, Aixin and Xue, Bing and Wang, Bingxuan and Wu, Bochao and Feng, Bei and Lu, Chengda and Zhao, Chenggang and Deng, Chengqi and Ruan, Chong and Dai, Damai and Chen, Deli and Ji, Dongjie and Li, Erhang and Lin, Fangyun and Dai, Fucong and Luo, Fuli and Hao, Guangbo and Chen, Guanting and Li, Guowei and Zhang, H. and Xu, Hanwei and Ding, Honghui and Gao, Huazuo and Qu, Hui and Li, Hui and Guo, Jianzhong and Li, Jiashi and Chen, Jingchang and Yuan, Jingyang and Tu, Jinhao and Qiu, Junjie and Li, Junlong and Cai, J. L. and Ni, Jiaqi and Liang, Jian and Chen, Jin and Dong, Kai and Hu, Kai and You, Kaichao and Gao, Kaige and Guan, Kang and Huang, Kexin and Yu, Kuai and Wang, Lean and Zhang, Lecong and Zhao, Liang and Wang, Litong and Zhang, Liyue and Xu, Lei and Xia, Leyi and Zhang, Mingchuan and Zhang, Minghua and Tang, Minghui and Zhou, Mingxu and Li, Meng and Wang, Miaojun and Li, Mingming and Tian, Ning and Huang, Panpan and Zhang, Peng and Wang, Qiancheng and Chen, Qinyu and Du, Qiushi and Ge, Ruiqi and Zhang, Ruisong and Pan, Ruizhe and Wang, Runji and Chen, R. J. and Jin, R. L. and Chen, Ruyi and Lu, Shanghao and Zhou, Shangyan and Chen, Shanhuang and Ye, Shengfeng and Wang, Shiyu and Yu, Shuiping and Zhou, Shunfeng and Pan, Shuting and Li, S. S. and Zhou, Shuang and Wu, Shaoqing and Yun, Tao and Pei, Tian and Sun, Tianyu and Wang, T. and Zeng, Wangding and Liu, Wen and Liang, Wenfeng and Gao, Wenjun and Yu, Wenqin and Zhang, Wentao and Xiao, W. L. and An, Wei and Liu, Xiaodong and Wang, Xiaohan and Chen, Xiaokang and Nie, Xiaotao and Cheng, Xin and Liu, Xin and Xie, Xin and Liu, Xingchao and Yang, Xinyu and Li, Xinyuan and Su, Xuecheng and Lin, Xuheng and Li, X. Q. and Jin, Xiangyue and Shen, Xiaojin and Chen, Xiaosha and Sun, Xiaowen and Wang, Xiaoxiang and Song, Xinnan and Zhou, Xinyi and Wang, Xianzu and Shan, Xinxia and Li, Y. K. and Wang, Y. Q. and Wei, Y. X. and Zhang, Yang and Xu, Yanhong and Li, Yao and Zhao, Yao and Sun, Yaofeng and Wang, Yaohui and Yu, Yi and Zhang, Yichao and Shi, Yifan and Xiong, Yiliang and He, Ying and Piao, Yishi and Wang, Yisong and Tan, Yixuan and Ma, Yiyang and Liu, Yiyuan and Guo, Yongqiang and Ou, Yuan and Wang, Yuduan and Gong, Yue and Zou, Yuheng and He, Yujia and Xiong, Yunfan and Luo, Yuxiang and You, Yuxiang and Liu, Yuxuan and Zhou, Yuyang and Zhu, Y. X. and Huang, Yanping and Li, Yaohui and Zheng, Yi and Zhu, Yuchen and Ma, Yunxian and Tang, Ying and Zha, Yukun and Yan, Yuting and Ren, Z. Z. and Ren, Zehui and Sha, Zhangli and Fu, Zhe and Xu, Zhean and Xie, Zhenda and Zhang, Zhengyan and Hao, Zhewen and Ma, Zhicheng and Yan, Zhigang and Wu, Zhiyu and Gu, Zihui and Zhu, Zijia and Liu, Zijun and Li, Zilin and Xie, Ziwei and Song, Ziyang and Pan, Zizheng and Huang, Zhen and Xu, Zhipeng and Zhang, Zhongyu and Zhang, Zhen}, journal = {Nature}, year = {2025}, volume = {645}, number = {8081}, pages = {633--638}, doi = {10.1038/s41586-025-09422-z} } @inproceedings{park2025deepvideor1, title = {DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-Aware Regressive GRPO}, author = {Park, Jinyoung and Na, Jeehye and Kim, Jinyoung and Kim, Hyunwoo J.}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {138605--138632}, doi = {10.52202/085713-4626} } @inproceedings{li2026deform360, title = {Deform360: A Massive Multi-View Visuotactile Dataset for Deformable World Models}, author = {Li, Hongyu and Fu, Wanjia and Cong, Xiaoyan and Li, Zekun and Huang, Binghao and Jiang, Hanxiao and He, Xintong and Liang, Yiqing and Fu, Rao and Lu, Tao and Sridhar, Srinath and Smith, Kevin A. and Konidaris, George and Li, Yunzhu}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {152--172}, doi = {10.1007/978-3-032-37447-9_9} } @misc{wu2026deltaforcing, title = {Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation}, author = {Yuheng Wu and Xiangbo Gao and Tianhao Chen and Xinghao Chen and Qing Yin and Zhengzhong Tu and Dongman Lee}, year = {2026}, eprint = {2605.14382}, archiveprefix = {arXiv} } @inproceedings{song2021ddim, title = {Denoising Diffusion Implicit Models}, author = {Jiaming Song and Chenlin Meng and Stefano Ermon}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2021} } @inproceedings{ho2020denoising, title = {Denoising Diffusion Probabilistic Models}, author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter}, booktitle = {Advances in Neural Information Processing Systems}, year = {2020}, volume = {33}, pages = {6840--6851} } @inproceedings{Krishna_2017_ICCV, title = {Dense-Captioning Events in Videos}, author = {Krishna, Ranjay and Hata, Kenji and Ren, Frederic and Fei-Fei, Li and Niebles, Juan Carlos}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, year = {2017}, pages = {706--715}, doi = {10.1109/iccv.2017.83} } @inproceedings{lei2021qvhighlights, title = {Detecting Moments and Highlights in Videos via Natural Language Queries}, author = {Lei, Jie and Berg, Tamara L and Bansal, Mohit}, booktitle = {Advances in Neural Information Processing Systems}, year = {2021}, volume = {34}, pages = {11846--11858}, } @misc{li2024dicode, title = {DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models}, author = {Yizhuo Li and Yuying Ge and Yixiao Ge and Ying Shan and Ping Luo}, year = {2024}, eprint = {2412.04446}, archiveprefix = {arXiv} } @inproceedings{lin2025seaweedapt, title = {Diffusion Adversarial Post-Training for One-Step Video Generation}, author = {Lin, Shanchuan and Xia, Xin and Ren, Yuxi and Yang, Ceyuan and Xiao, Xuefeng and Jiang, Lu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {37959--37974}, } @inproceedings{alonso2024diamond, title = {Diffusion for World Modeling: Visual Details Matter in Atari}, author = {Alonso, Eloi and Jelley, Adam and Micheli, Vincent and Kanervisto, Anssi and Storkey, Amos and Pearce, Tim and Fleuret, François}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {58757--58791}, doi = {10.52202/079017-1873} } @inproceedings{chen2024diffusionforcing, title = {Diffusion Forcing: Next-Token Prediction Meets Full-Sequence Diffusion}, author = {Chen, Boyuan and Martí Monsó, Diego and Du, Yilun and Simchowitz, Max and Tedrake, Russ and Sitzmann, Vincent}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {24081--24125}, doi = {10.52202/079017-0759} } @inproceedings{valevski2025gamengen, title = {Diffusion Models Are Real-Time Game Engines}, author = {Dani Valevski and Yaniv Leviathan and Moab Arar and Shlomi Fruchter}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{epstein2023selfguidance, title = {Diffusion Self-Guidance for Controllable Image Generation}, author = {Epstein, Dave and Jabri, Allan and Poole, Ben and Efros, Alexei A. and Holynski, Aleksander}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {16222--16239}, doi = {10.52202/075280-0714} } @inproceedings{zhou2024dinowm, title = {{DINO}-{WM}: World Models on Pre-Trained Visual Features Enable Zero-Shot Planning}, author = {Zhou, Gaoyue and Pan, Hengkai and Lecun, Yann and Pinto, Lerrel}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {79115--79135}, } @misc{hu2026divid, title = {{DiVid}: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models}, author = {Huanran Hu and Zihui Ren and Dingyi Yang and Zhinan Song and Guozheng Wu and Tiezheng Ge and Qin Jin}, year = {2026}, eprint = {2610.01661}, archiveprefix = {arXiv} } @inproceedings{ge2024divot, title = {{Divot}: Diffusion Powers Video Tokenizer for Comprehension and Generation}, author = {Ge, Yuying and Li, Yizhuo and Ge, Yixiao and Shan, Ying}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {13606--13617}, doi = {10.1109/cvpr52734.2025.01270} } @inproceedings{ling2024dl3dv, title = {DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-Based 3D Vision}, author = {Ling, Lu and Sheng, Yichen and Tu, Zhi and Zhao, Wentian and Xin, Cheng and Wan, Kun and Yu, Lantao and Guo, Qianyu and Yu, Zixun and Lu, Yawen and Li, Xuanmao and Sun, Xingpeng and Ashok, Rohan and Mukherjee, Aniruddha and Kang, Hao and Kong, Xiangrui and Hua, Gang and Zhang, Tianyi and Benes, Bedrich and Bera, Aniket}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {22160--22169}, doi = {10.1109/cvpr52733.2024.02092} } @misc{zhang2026dmccf, title = {DMC-CF: Dynamic Multimodal CounterFactual QA Benchmark for Causal Reasoning}, author = {Junzhe Zhang and Huixuan Zhang and Guirong Wang and Xingyao Zhang and Pei Liu and Lin Qu and Hu Wei and Xiaojun Wan}, year = {2026}, eprint = {2605.29339}, archiveprefix = {arXiv} } @inproceedings{motamed2025physicsiq, title = {Do Generative Video Models Understand Physical Principles?}, author = {Motamed, Saman and Culp, Laura and Swersky, Kevin and Jaini, Priyank and Geirhos, Robert}, booktitle = {2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, year = {2026}, pages = {948--958}, doi = {10.1109/wacv61042.2026.00099} } @misc{niu2025understandinginformgenerationunified, title = {Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward}, author = {Yuwei Niu and Weiyang Jin and Jiaqi Liao and Chaoran Feng and Peng Jin and Bin Lin and Zongjian Li and Bin Zhu and Weihao Yu and Li Yuan}, year = {2025}, eprint = {2511.20561}, archiveprefix = {arXiv} } @article{luo2026dr, title = {{Dr. V}: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-Grained Spatial-Temporal Grounding}, author = {Luo, Meng and Wu, Shengqiong and Jing, Liqiang and Ju, Tianjie and Zheng, Li and Lai, Jinxiang and Wu, Tianlong and Du, Xinya and Li, Jian and Yan, Siyuan and Luo, Jiebo and Wang, William Yang and Fei, Hao and Lee, Mong-Li and Hsu, Wynne}, journal = {International Journal of Computer Vision}, year = {2026}, volume = {134}, number = {6}, pages = {278}, doi = {10.1007/s11263-026-02831-1} } @misc{yin2023dragnuwa, title = {DragNUWA: Fine-Grained Control in Video Generation by Integrating Text, Image, and Trajectory}, author = {Shengming Yin and Chenfei Wu and Jian Liang and Jie Shi and Houqiang Li and Gong Ming and Nan Duan}, year = {2023}, eprint = {2308.08089}, archiveprefix = {arXiv} } @inproceedings{ruiz2023dreambooth, title = {{DreamBooth}: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation}, author = {Ruiz, Nataniel and Li, Yuanzhen and Jampani, Varun and Pritch, Yael and Rubinstein, Michael and Aberman, Kfir}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {22500--22510}, doi = {10.1109/cvpr52729.2023.02155} } @inproceedings{gao2026dreamdojo, title = {{D}ream{D}ojo: A Generalist Robot World Model from Large-Scale Human Videos}, author = {Gao, Shenyuan and Liang, William and Zheng, Kaiyuan and Malik, Ayaan Naveed and Ye, Seonghyeon and Yu, Sihyun and Tseng, Wei-Cheng and Dong, Yuzhu and Mo, Kaichun and Lin, Chen-Hsuan and Xiang, Jiannan and Xie, Yuqi and Zheng, Ruijie and Niu, Dantong and Jannaty, Pooya and Gu, Jinwei and Zhang, Jun and Malik, Jitendra and Abbeel, Pieter and Liu, Ming-Yu and Zhu, Yuke and Jang, Joel and Fan, Linxi}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {33340--33366}, } @inproceedings{jang2025dreamgen, title = {DreamGen: Unlocking Generalization in Robot Learning Through Video World Models}, author = {Jang, Joel and Ye, Seonghyeon and Lin, Zongyu and Xiang, Jiannan and Bjorck, Johan and Fang, Yu and Hu, Fengyuan and Huang, Spencer and Kundalia, Kaushil and Lin, Yen-Chen and Magne, Lo\"{i}c and Mandlekar, Ajay and Narayan, Avnish and Tan, You Liang and Wang, Guanzhi and Wang, Jing and Wang, Qi and Xu, Yinzhen and Zeng, Xiaohui and Zheng, Kaiyuan and Zheng, Ruijie and Liu, Ming-Yu and Zettlemoyer, Luke and Fox, Dieter and Kautz, Jan and Reed, Scott and Zhu, Yuke and Fan, Linxi}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, year = {2025}, volume = {305}, pages = {5170--5194}, } @inproceedings{liang2024dreamitate, title = {Dreamitate: Real-World Visuomotor Policy Learning via Video Generation}, author = {Liang, Junbang and Liu, Ruoshi and Ozguroglu, Ege and Sudhakar, Sruthi and Dave, Achal and Tokmakov, Pavel and Song, Shuran and Vondrick, Carl}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, year = {2025}, volume = {270}, pages = {3943--3960}, } @inproceedings{dong2023dreamllm, title = {DreamLLM: Synergistic Multimodal Comprehension and Creation}, author = {Dong, Runpei and Han, Chunrui and Peng, Yuang and Qi, Zekun and Ge, Zheng and Yang, Jinrong and Zhao, Liang and Sun, Jianjian and Zhou, Hongyu and Wei, Haoran and Kong, Xiangwen and Zhang, Xiangyu and Ma, Kaisheng and Yi, Li}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{wang2024drivedreamer, title = {DriveDreamer: Towards Real-World-Driven World Models for Autonomous Driving}, author = {Xiaofeng Wang and Zheng Zhu and Guan Huang and Xinze Chen and Jiagang Zhu and Jiwen Lu}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, doi = {10.1007/978-3-031-73195-2_4} } @inproceedings{sima2024drivelm, title = {DriveLM: Driving with Graph Visual Question Answering}, author = {Chonghao Sima and Katrin Renz and Kashyap Chitta and Li Chen and Hanxue Zhang and Chengen Xie and Jens Beißwenger and Ping Luo and Andreas Geiger and Hongyang Li}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, doi = {10.1007/978-3-031-72943-0_15} } @inproceedings{zhou2026drivinggen, title = {DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving}, author = {Zhou, Yang and Shao, Hao and Wang, Letian and Zong, Zhuofan and Li, Hongsheng and Waslander, Steven L.}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{hu2024drivingworld, title = {DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT}, author = {Hu, Xiaotao and Jia, Mingkai and Guo, Xiaoyang and Zhang, Qian and Long, Xiao-xiao and Yin, Wei}, booktitle = {Pattern Recognition (ICPR 2026)}, year = {2027}, volume = {16813}, pages = {276--291}, doi = {10.1007/978-3-032-31583-0_19}, } @inproceedings{khazatsky2024droid, title = {DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset}, author = {Alexander Khazatsky and Karl Pertsch and Suraj Nair and Ashwin Balakrishna and Sudeep Dasari and Siddharth Karamcheti and Soroush Nasiriany and Mohan Kumar Srirama and Lawrence Yunliang Chen and Kirsty Ellis and Peter David Fagan and Joey Hejna and Masha Itkina and Marion Lepert and Jason Ma and Patrick Tree Miller and Jimmy Wu and Suneel Belkhale and Shivin Dass and Huy Ha and Abraham Lee and Youngwoon Lee and Arhan Jain and Marius Memmel and Sungjae Park and Ilija Radosavovic and Kaiyuan Wang and Albert Zhan and Kevin Black and Cheng Chi and Kyle Hatch and Shan Lin and Jingpei Lu and Abdul Rehman and Pannag R Sanketi and Archit Sharma and Cody Simpson and Quan Vuong and Homer Walke and Blake Wulfe and Ted Xiao and Jonathan Yang and Arefeh Yavary and Tony Z. Zhao and Christopher Agia and Rohan Baijal and Mateo Guaman Castro and Daphne Chen and Qiuyu Chen and Trinity Chung and Jaimyn Drake and Ethan Paul Foster and Jensen Gao and David Antonio Herrera and Minho Heo and Kyle Hsu and Jiaheng Hu and Donovon Jackson and Charlotte Le and Yunshuang Li and Kevin Lin and Roy Lin and Zehan Ma and Abhiram Maddukuri and Suvir Mirchandani and Daniel Morton and Tony Nguyen and Abby O’Neill and Rosario Scalise and Derick Seale and Victor Son and Stephen Tian and Andrew Wang and Yilin Wu and Annie Xie and Jingyun Yang and Patrick Yin and Yunchu Zhang and Osbert Bastani and Glen Berseth and Jeannette Bohg and Ken Goldberg and Abhinav Gupta and Abhishek Gupta and Dinesh Jayaraman and Joseph J. Lim and Jitendra Malik and Roberto Martín-Martín and Subramanian Ramamoorthy and Dorsa Sadigh and Shuran Song and Jiajun Wu and Yuke Zhu and Thomas Kollar and Sergey Levine and Chelsea Finn}, booktitle = {Proceedings of Robotics: Science and Systems}, year = {2024}, doi = {10.15607/RSS.2024.XX.120} } @misc{zhang2025dsibench, title = {DSI-Bench: A Benchmark for Dynamic Spatial Intelligence}, author = {Ziang Zhang and Zehan Wang and Guanghao Zhang and Weilong Dai and Yan Xia and Ziang Yan and Minjie Hong and Zhou Zhao}, year = {2025}, eprint = {2510.18873}, archiveprefix = {arXiv} } @inproceedings{fei2024dysenvdm, title = {{Dysen-VDM}: Empowering Dynamics-Aware Text-to-Video Diffusion with {LLMs}}, author = {Fei, Hao and Wu, Shengqiong and Ji, Wei and Zhang, Hanwang and Chua, Tat-Seng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {7641--7653}, doi = {10.1109/cvpr52733.2024.00730} } @misc{yang2026eawm, title = {EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields}, author = {Zhaoyang Yang and Yurun Jin and Lizhe Qi and Cong Huang and Kai Chen}, year = {2026}, eprint = {2605.06192}, archiveprefix = {arXiv} } @inproceedings{chen2025eagle25, title = {Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models}, author = {Chen, Guo and Li, Zhiqi and Wang, Shihao and Jiang, Jindong and Liu, Yicheng and Lu, Lidong and Huang, De-An and Byeon, Wonmin and Le, Matthieu and Ehrlich, Max and Lu, Tong and Wang, Limin and Catanzaro, Bryan and Kautz, Jan and Tao, Andrew and Yu, Zhiding and Liu, Guilin}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {91077--91100}, doi = {10.52202/085713-3047} } @misc{bian2026echoinfinity, title = {Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation}, author = {Yuxuan Bian and Zeyue Xue and Songchun Zhang and Shiyi Zhang and Weiyang Jin and Yaowei Li and Junhao Zhuang and Haoran Li and Jie Huang and Haoyang Huang and Nan Duan and Qiang Xu}, year = {2026}, eprint = {2606.04527}, archiveprefix = {arXiv} } @misc{zhu2026efficient, title = {Efficient Universal Perception Encoder}, author = {Zhu, Chenchen and Suri, Saksham and Jose, Cijo and Oquab, Maxime and Szafraniec, Marc and Wen, Wei and Xiong, Yunyang and Labatut, Patrick and Bojanowski, Piotr and Krishnamoorthi, Raghuraman and Chandra, Vikas}, year = {2026}, eprint = {2603.22387}, archiveprefix = {arXiv} } @article{grauman2024egoexo4d, title = {Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives}, author = {Grauman, Kristen and Westbury, Andrew and Torresani, Lorenzo and Kitani, Kris and Malik, Jitendra and Afouras, Triantafyllos and Ashutosh, Kumar and Baiyya, Vijay and Bansal, Siddhant and Boote, Bikram and Byrne, Eugene and Chavis, Zach and Chen, Joya and Cheng, Feng and Chu, Fu-Jen and Crane, Sean and Dasgupta, Avijit and Dong, Jing and Escobar, Maria and Forigua, Cristhian and Gebreselasie, Abrham and Haresh, Sanjay and Huang, Jing and Islam, Md Mohaiminul and Jain, Suyog and Khirodkar, Rawal and Kukreja, Devansh and Liang, Kevin J. and Liu, Jia-Wei and Majumder, Sagnik and Mao, Yongsen and Martin, Miguel and Mavroudi, Effrosyni and Nagarajan, Tushar and Ragusa, Francesco and Ramakrishnan, Santhosh Kumar and Seminara, Luigi and Somayazulu, Arjun and Song, Yale and Su, Shan and Xue, Zihui and Zhang, Edward and Zhang, Jinxu and Castillo, Angela and Chen, Changan and Fu, Xinzhu and Furuta, Ryosuke and González, Cristina and Gupta, Prince and Hu, Jiabo and Huang, Yifei and Huang, Yiming and Khoo, Weslie and Kumar, Anush and Kuo, Robert and Lakhavani, Sach and Liu, Miao and Luo, Mi and Luo, Zhengyi and Meredith, Brighid and Miller, Austin and Oguntola, Oluwatumininu and Pan, Xiaqing and Peng, Penny and Pramanick, Shraman and Ramazanova, Merey and Ryan, Fiona and Shan, Wei and Somasundaram, Kiran and Song, Chenan and Southerland, Audrey and Tateno, Masatoshi and Wang, Huiyu and Wang, Yuchen and Yagi, Takuma and Yan, Mingfei and Yang, Xitong and Yu, Zecheng and Zha, Shengxin Cindy and Zhao, Chen and Zhao, Ziwei and Zhu, Zhifan and Zhuo, Jeff and Arbeláez, Pablo and Bertasius, Gedas and Crandall, David and Damen, Dima and Engel, Jakob and Farinella, Giovanni Maria and Furnari, Antonino and Ghanem, Bernard and Hoffman, Judy and Jawahar, C. V. and Newcombe, Richard and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Savva, Manolis and Shi, Jianbo and Shou, Mike Zheng and Wray, Michael}, journal = {International Journal of Computer Vision}, year = {2025}, volume = {133}, number = {12}, pages = {8356--8435}, doi = {10.1007/s11263-025-02557-6} } @article{tian2025egor1, title = {Ego-R1: Agentic Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning}, author = {Tian, Shulin and Wang, Ruiqi and Guo, Hongming and Wu, Penghao and Dong, Yuhao and Wang, Xiuying and Yang, Jingkang and Zhang, Hao and Zhu, Hongyuan and Liu, Ziwei}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, year = {2026}, volume = {48}, number = {10}, pages = {12116--12131}, doi = {10.1109/tpami.2026.3697367} } @inproceedings{grauman2022ego4d, title = {Ego4D: Around the World in 3,000 Hours of Egocentric Video}, author = {Grauman, Kristen and Westbury, Andrew and Byrne, Eugene and Chavis, Zachary and Furnari, Antonino and Girdhar, Rohit and Hamburger, Jackson and Jiang, Hao and Liu, Miao and Liu, Xingyu and Martin, Miguel and Nagarajan, Tushar and Radosavovic, Ilija and Ramakrishnan, Santhosh Kumar and Ryan, Fiona and Sharma, Jayant and Wray, Michael and Xu, Mengmeng and Xu, Eric Zhongcong and Zhao, Chen and Bansal, Siddhant and Batra, Dhruv and Cartillier, Vincent and Crane, Sean and Do, Tien and Doulaty, Morrie and Erapalli, Akshay and Feichtenhofer, Christoph and Fragomeni, Adriano and Fu, Qichen and Gebreselasie, Abrham and Gonz\'alez, Cristina and Hillis, James and Huang, Xuhua and Huang, Yifei and Jia, Wenqi and Khoo, Weslie and Kol\'a\v{r}, J\'achym and Kottur, Satwik and Kumar, Anurag and Landini, Federico and Li, Chao and Li, Yanghao and Li, Zhenqiang and Mangalam, Karttikeya and Modhugu, Raghava and Munro, Jonathan and Murrell, Tullie and Nishiyasu, Takumi and Price, Will and Ruiz Puentes, Paola and Ramazanova, Merey and Sari, Leda and Somasundaram, Kiran and Southerland, Audrey and Sugano, Yusuke and Tao, Ruijie and Vo, Minh and Wang, Yuchen and Wu, Xindi and Yagi, Takuma and Zhao, Ziwei and Zhu, Yunyi and Arbel\'aez, Pablo and Crandall, David and Damen, Dima and Farinella, Giovanni Maria and Fuegen, Christian and Ghanem, Bernard and Ithapu, Vamsi Krishna and Jawahar, C. V. and Joo, Hanbyul and Kitani, Kris and Li, Haizhou and Newcombe, Richard and Oliva, Aude and Park, Hyun Soo and Rehg, James M. and Sato, Yoichi and Shi, Jianbo and Shou, Mike Zheng and Torralba, Antonio and Torresani, Lorenzo and Yan, Mingfei and Malik, Jitendra}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {18995--19012}, doi = {10.1109/cvpr52688.2022.01842} } @inproceedings{yang2025egolife, title = {EgoLife: Towards Egocentric Life Assistant}, author = {Yang, Jingkang and Liu, Shuai and Guo, Hongming and Dong, Yuhao and Zhang, Xiamengwei and Zhang, Sicheng and Wang, Pengyun and Zhou, Zitang and Xie, Binzhu and Wang, Ziyue and Ouyang, Bei and Lin, Zhengyu and Cominelli, Marco and Cai, Zhongang and Li, Bo and Zhang, Yuanhan and Zhang, Peiyuan and Hong, Fangzhou and Widmer, Joerg and Gringoli, Francesco and Yang, Lei and Liu, Ziwei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {28885--28900}, doi = {10.1109/cvpr52734.2025.02690} } @inproceedings{egopolice2026, title = {EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage}, author = {Gonzalez Saez-Diez, Max and Chung, Jihoon and Wolsky, Adam D. and Lanzalotto, Gregory and Knox, Dean and Mummolo, Jonathan and Stewart, Brandon M. and Russakovsky, Olga}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {362--379}, doi = {10.1007/978-3-032-37520-9_20} } @inproceedings{mangalam2023egoschema, title = {EgoSchema: A Diagnostic Benchmark for Very Long-Form Video Language Understanding}, author = {Karttikeya Mangalam and Raiymbek Akshkulakov and Jitendra Malik}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {46212--46244}, doi = {10.52202/075280-2004} } @misc{tian2026egotools, title = {{EgoTools}: Towards Tool-Centric Reasoning in Real-World Egocentric Videos}, author = {Shulin Tian and Junsu Kim and Shuai Liu and Hao Li and Yujiao Shen and Sihan Li and Zhe Yang and Yeongon Kim and Feiyu Li and Jialin Wu and Yichi Zhang and Wenhui Wang and Runmao Yao and Yuhao Dong and Zhaoxi Chen and Fangzhou Hong and Antonino Furnari and Jingkang Yang and Hongyuan Zhu and Ziwei Liu}, year = {2026}, eprint = {2609.39378}, archiveprefix = {arXiv} } @misc{deng2505emerging, title = {Emerging Properties in Unified Multimodal Pretraining}, author = {Chaorui Deng and Deyao Zhu and Kunchang Li and Chenhui Gou and Feng Li and Zeyu Wang and Shu Zhong and Weihao Yu and Xiaonan Nie and Ziang Song and Guang Shi and Haoqi Fan}, year = {2025}, eprint = {2505.14683}, archiveprefix = {arXiv} } @inproceedings{tian2024emo, title = {EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model Under Weak Conditions}, author = {Linrui Tian and Qi Wang and Bang Zhang and Liefeng Bo}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, pages = {244--260}, doi = {10.1007/978-3-031-73010-8_15}, organization = {Springer} } @misc{cui2025emu3, title = {{Emu3.5}: Native Multimodal Models Are World Learners}, author = {Cui, Yufeng and Chen, Honghao and Deng, Haoge and Huang, Xu and Li, Xinghang and Liu, Jirong and Liu, Yang and Luo, Zhuoyan and Wang, Jinsheng and Wang, Wenxuan and Wang, Yueze and Wang, Chengyuan and Zhang, Fan and Zhao, Yingli and Pan, Ting and Li, Xianduo and Hao, Zecheng and Ma, Wenxuan and Chen, Zhuo and Ao, Yulong and Huang, Tiejun and Wang, Zhongyuan and Wang, Xinlong}, year = {2025}, eprint = {2510.26583}, archiveprefix = {arXiv} } @misc{wang2024emu3, title = {Emu3: Next-Token Prediction Is All You Need}, author = {Xinlong Wang and Xiaosong Zhang and Zhengxiong Luo and Quan Sun and Yufeng Cui and Jinsheng Wang and Fan Zhang and Yueze Wang and Zhen Li and Qiying Yu and Yingli Zhao and Yulong Ao and Xuebin Min and Tao Li and Boya Wu and Bo Zhao and Bowen Zhang and Liangdong Wang and Guang Liu and Zheqi He and Xi Yang and Jingjing Liu and Yonghua Lin and Tiejun Huang and Zhongyuan Wang}, year = {2024}, eprint = {2409.18869}, archiveprefix = {arXiv} } @article{twinanda2016endonet, title = {EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos}, author = {Twinanda, Andru P. and Shehata, Sherif and Mutter, Didier and Marescaux, Jacques and de Mathelin, Michel and Padoy, Nicolas}, journal = {IEEE Transactions on Medical Imaging}, year = {2017}, volume = {36}, number = {1}, pages = {86--97}, doi = {10.1109/tmi.2016.2593957} } @article{fei2024finsta, title={Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment}, author={Fei, Hao and Wu, Shengqiong and Zhang, Meishan and Zhang, Min and Chua, Tat-Seng and Yan, Shuicheng}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume={46}, number={12}, pages={7701--7719}, year={2024}, doi={10.1109/TPAMI.2024.3393452} } @inproceedings{shi2024aotd, title = {Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation}, author = {Shi, Yudi and Di, Shangzhe and Chen, Qirui and Xie, Weidi}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {8523--8533}, doi = {10.1109/cvpr52734.2025.00797} } @misc{chi2024eva, title = {EVA: An Embodied World Model for Future Video Anticipation}, author = {Xiaowei Chi and Chun-Kai Fan and Hengyuan Zhang and Xingqun Qi and Rongyu Zhang and Anthony Chen and Chi-min Chan and Wei Xue and Qifeng Liu and Shanghang Zhang and Yike Guo}, year = {2024}, eprint = {2410.15461}, archiveprefix = {arXiv} } @inproceedings{zhang2026evaagent, title = {EVA: Efficient Reinforcement Learning for End-to-End Video Agent}, author = {Zhang, Yaolun and Wang, Ruohui and Wang, Jiahao and Tang, Yepeng and Zheng, Xuanyu and Duan, Haonan and Lu, Hao and Deng, Hanming and Lu, Lewei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {12289--12299}, } @inproceedings{liu2024evalcrafterbenchmarkingevaluatinglarge, title = {EvalCrafter: Benchmarking and Evaluating Large Video Generation Models}, author = {Liu, Yaofang and Cun, Xiaodong and Liu, Xuebo and Wang, Xintao and Zhang, Yong and Chen, Haoxin and Liu, Yang and Zeng, Tieyong and Chan, Raymond and Shan, Ying}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {22139--22149}, doi = {10.1109/cvpr52733.2024.02090} } @inproceedings{pasukonis2022memorymaze, title = {Evaluating Long-Term Memory in 3D Mazes}, author = {Pasukonis, Jurgis and Lillicrap, Timothy and Hafner, Danijar}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{mmecofpro2026, title = {Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints}, author = {Yu Qi and Xinyi Xu and Ziyu Guo and Siyuan Ma and Renrui Zhang and Xinyan Chen and Ruichuan An and Ruofan Xing and Jiayi Zhang and Haojie Huang and Pheng-Ann Heng and Jonathan Tremblay and Lawson L. S. Wong}, booktitle = {Computer Vision -- ECCV 2026}, year = {2026}, volume = {17037}, pages = {76--93}, doi = {10.1007/978-3-032-37467-7_5} } @inproceedings{koo2025cfred, title = {Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Frechet Distance}, author = {Koo, Jaywon and Hernandez, Jefferson and Haji-Ali, Moayed and Yang, Ziyan and Ordonez, Vicente}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, year = {2026}, pages = {2052--2062}, doi = {10.1109/wacv61042.2026.00204} } @inproceedings{xiong2026evatok, title = {EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation}, author = {Xiong, Tianwei and Liew, Jun Hao and Huang, Zilong and Lin, Zhijie and Feng, Jiashi and Liu, Xihui}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {23249--23259}, } @misc{zhang2024eventhallusion, title = {EventHallusion: Diagnosing Event Hallucinations in Video LLMs}, author = {Jiacheng Zhang and Yang Jiao and Shaoxiang Chen and Na Zhao and Zhiyu Tan and Hao Li and Xingjun Ma and Jingjing Chen}, year = {2024}, eprint = {2409.16597}, archiveprefix = {arXiv} } @misc{wang2026ewam, title = {EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding Through Visual Foresight to Action}, author = {Hao Wang and Jiajun Wen and Jingzhi Liu and Shuoshuo Xue and Zhiliang Chen and Min Lin and Yicheng Chang and Xiaoyu Guo and Yukang Zhuo and Zheng Chong and Yunshuang Nie and Jian Zhang and Weijia Liufu and Qingman Wu and Heming Xu and Bingchang Song and Dantong Wu and Zhiyuan Wang and Hang Xu and Jianhua Han and Bokui Chen and Shen Zhao and Rui Li and Xiaodan Liang}, year = {2026}, eprint = {2609.39973}, archiveprefix = {arXiv} } @misc{ewmbench2025, title = {EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models}, author = {Hu Yue and Siyuan Huang and Yue Liao and Shengcong Chen and Pengfei Zhou and Liliang Chen and Maoqing Yao and Guanghui Ren}, year = {2025}, eprint = {2505.09694}, archiveprefix = {arXiv} } @misc{lin2025metacanvas, title = {Exploring MLLM-Diffusion Information Transfer with MetaCanvas}, author = {Han Lin and Xichen Pan and Ziqi Huang and Ji Hou and Jialiang Wang and Weifeng Chen and Zecheng He and Felix Juefei-Xu and Junzhe Sun and Zhipeng Fan and Ali Thabet and Mohit Bansal and Chu Wang}, year = {2025}, eprint = {2512.11464}, archiveprefix = {arXiv} } @inproceedings{lv2024fastercache, title = {FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality}, author = {Lv, Zhengyao and Si, Chenyang and Song, Junhao and Yang, Zhenyu and Qiao, Yu and Liu, Ziwei and Wong, Kwan-Yee K.}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{qi2023fatezero, title = {FateZero: Fusing Attentions for Zero-Shot Text-Based Video Editing}, author = {Qi, Chenyang and Cun, Xiaodong and Zhang, Yong and Lei, Chenyang and Wang, Xintao and Shan, Ying and Chen, Qifeng}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {15932--15942}, doi = {10.1109/iccv51070.2023.01460} } @inproceedings{liu2023fetvbenchmarkfinegrainedevaluation, title = {FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation}, author = {Liu, Yuanxin and Li, Lei and Ren, Shuhuai and Gao, Rundong and Li, Shicheng and Chen, Sishuo and Sun, Xu and Hou, Lu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {62352--62387}, doi = {10.52202/075280-2723} } @inproceedings{wei2022finetuned, title = {Finetuned Language Models Are Zero-Shot Learners}, author = {Jason Wei and Maarten Bosma and Vincent Y. Zhao and Kelvin Guu and Adams Wei Yu and Brian Lester and Nan Du and Andrew M. Dai and Quoc V. Le}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @misc{wiedmann2025finevision, title = {FineVision: Open Data Is All You Need}, author = {Luis Wiedmann and Orr Zohar and Amir Mahla and Xiaohan Wang and Rui Li and Thibaud Frere and Leandro von Werra and Aritra Roy Gosthipaty and Andr{\'e}s Marafioti}, year = {2025}, eprint = {2510.17269}, archiveprefix = {arXiv} } @inproceedings{mentzer2024fsq, title = {Finite Scalar Quantization: VQ-VAE Made Simple}, author = {Mentzer, Fabian and Minnen, David and Agustsson, Eirikur and Tschannen, Michael}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{alayrac2022flamingo, title = {Flamingo: A Visual Language Model for Few-Shot Learning}, author = {Alayrac, Jean-Baptiste and Donahue, Jeff and Luc, Pauline and Miech, Antoine and Barr, Iain and Hasson, Yana and Lenc, Karel and Mensch, Arthur and Millican, Katie and Reynolds, Malcolm and Ring, Roman and Rutherford, Eliza and Cabi, Serkan and Han, Tengda and Gong, Zhitao and Samangooei, Sina and Monteiro, Marianne and Menick, Jacob and Borgeaud, Sebastian and Brock, Andrew and Nematzadeh, Aida and Sharifzadeh, Sahand and Bińkowski, Mikołaj and Barreira, Ricardo and Vinyals, Oriol and Zisserman, Andrew and Simonyan, Karén}, booktitle = {Advances in Neural Information Processing Systems}, year = {2022}, volume = {35}, pages = {23716--23736}, doi = {10.52202/068431-1723} } @misc{khorrambakht2026flexwam, title = {{FLEX-WAM}: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning}, author = {Khorrambakht, R. and Amigo, Joseph and Lebel, F{\'e}lix and Seetoo, Leon and Ponce, Jean and Li, Zhenzhen and Righetti, Ludovic}, year = {2026}, eprint = {2610.05483}, archiveprefix = {arXiv} } @inproceedings{lipman2023flow, title = {Flow Matching for Generative Modeling}, author = {Yaron Lipman and Ricky T. Q. Chen and Heli Ben-Hamu and Maximilian Nickel and Matt Le}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{zhang2025framepack, title = {Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models}, author = {Zhang, Lvmin and Cai, Shengqu and Li, Muyang and Wetzstein, Gordon and Agrawala, Maneesh}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {30546--30566}, doi = {10.52202/085713-1024} } @inproceedings{he2025framethinker, title = {FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting}, author = {He, Zefeng and Qu, Xiaoye and Li, Yafu and Huang, Siyuan and Liu, Daizong and Cheng, Yu}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{yu2023freedom, title = {FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model}, author = {Yu, Jiwen and Wang, Yinhuai and Zhao, Chen and Ghanem, Bernard and Zhang, Jian}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {23174--23184}, doi = {10.1109/iccv51070.2023.02118} } @inproceedings{lu2024freelong, title = {FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention}, author = {Lu, Yu and Liang, Yuanzhi and Zhu, Linchao and Yang, Yi}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {131434--131455}, doi = {10.52202/079017-4177} } @inproceedings{luo2026evaluation, title = {From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models}, author = {Luo, Meng and Liu, Yicheng and Wang, Jiahao and Zhang, Yuanxing and Tao, Xin and Wan, Pengfei and Gai, Kun and Fei, Hao}, booktitle = {European Conference on Computer Vision (ECCV)}, year = {2026}, pages = {546--563}, doi = {10.1007/978-3-032-37595-7_30} } @inproceedings{yin2025causvid, title = {From Slow Bidirectional to Fast Autoregressive Video Diffusion Models}, author = {Yin, Tianwei and Zhang, Qiang and Zhang, Richard and Freeman, William T. and Durand, Frédo and Shechtman, Eli and Huang, Xun}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {22963--22974}, doi = {10.1109/cvpr52734.2025.02138} } @inproceedings{mmmem2026, title = {From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents}, author = {Lian, Niu and Wang, Yuting and Yao, Hanshu and Wang, Jinpeng and Chen, Bin and Wang, Yaowei and Zhang, Min and Xia, Shu-Tao}, booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2026}, pages = {11601--11617}, doi = {10.18653/v1/2026.acl-long.533}, } @inproceedings{Bain_2021_ICCV, title = {Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval}, author = {Bain, Max and Nagrani, Arsha and Varol, G{\"u}l and Zisserman, Andrew}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2021}, pages = {1728--1738}, doi = {10.1109/iccv48922.2021.00175} } @inproceedings{kilgour2018fad, title = {Fréchet Audio Distance: A Reference-Free Metric for Evaluating Music Enhancement Algorithms}, author = {Kilgour, Kevin and Zuluaga, Mauricio and Roblek, Dominik and Sharifi, Matthew}, booktitle = {Interspeech 2019}, year = {2019}, pages = {2350--2354}, doi = {10.21437/interspeech.2019-2219} } @misc{liu2024fvmd, title = {Fr\'Echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos}, author = {Jiahe Liu and Youran Qu and Qi Yan and Xiaohui Zeng and Lele Wang and Renjie Liao}, year = {2024}, eprint = {2407.16124}, archiveprefix = {arXiv} } @inproceedings{fulldit2025, title = {{FullDiT: Video Generative Foundation Models with Multimodal Control via Full Attention}}, author = {Ju, Xuan and Ye, Weicai and Liu, Quande and Wang, Qiulin and Wang, Xintao and Wan, Pengfei and Zhang, Di and Gai, Kun and Xu, Qiang}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {15737--15747}, doi = {10.1109/iccv51701.2025.01460} } @misc{hu2023gaia1, title = {GAIA-1: A Generative World Model for Autonomous Driving}, author = {Anthony Hu and Lloyd Russell and Hudson Yeo and Zak Murez and George Fedoseev and Alex Kendall and Jamie Shotton and Gianluca Corrado}, year = {2023}, eprint = {2309.17080}, archiveprefix = {arXiv} } @misc{russell2025gaia2, title = {GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving}, author = {Lloyd Russell and Anthony Hu and Lorenzo Bertoni and George Fedoseev and Jamie Shotton and Elahe Arani and Gianluca Corrado}, year = {2025}, eprint = {2503.20523}, archiveprefix = {arXiv} } @misc{wayve2025gaia3, title = {GAIA-3: Scaling World Models to Power Safety and Evaluation}, author = {{Wayve}}, year = {2025}, howpublished = {Wayve technical publication} } @inproceedings{gamefactory2025, title = {GameFactory: Creating New Games with Generative Interactive Videos}, author = {Yu, Jiwen and Qin, Yiran and Wang, Xintao and Wan, Pengfei and Zhang, Di and Liu, Xihui}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {11590--11599}, doi = {10.1109/iccv51701.2025.01078} } @inproceedings{heusel2018ganstrainedtimescaleupdate, title = {GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium}, author = {Heusel, Martin and Ramsauer, Hubert and Unterthiner, Thomas and Nessler, Bernhard and Hochreiter, Sepp}, booktitle = {Advances in Neural Information Processing Systems}, year = {2017}, volume = {30}, } @misc{qiu2026gesim2, title = {GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-Loop Video World Simulators for Robotic Manipulation}, author = {Boxiang Qiu and Liliang Chen and Yue Liao and Nan Wang and Lintao Wang and Jiayi Luo and Wenzhi Zhao and Shengcong Chen and Di Chen and Ye Li and Chen Gao and Shuicheng Yan and Si Liu and Maoqing Yao and Guanghui Ren}, year = {2026}, eprint = {2605.27491}, archiveprefix = {arXiv} } @misc{gemini15_2024, title = {Gemini 1.5: Unlocking Multimodal Understanding Across Millions of Tokens of Context}, author = {Gemini Team and Petko Georgiev and Ving Ian Lei and Ryan Burnell and Libin Bai and Anmol Gulati and Garrett Tanzer and Damien Vincent and Zhufeng Pan and Shibo Wang and Soroosh Mariooryad and Yifan Ding and Xinyang Geng and Fred Alcober and Roy Frostig and Mark Omernick and Lexi Walker and Cosmin Paduraru and Christina Sorokin and Andrea Tacchetti and Colin Gaffney and Samira Daruki and Olcan Sercinoglu and Zach Gleicher and Juliette Love and Paul Voigtlaender and Rohan Jain and Gabriela Surita and Kareem Mohamed and Rory Blevins and Junwhan Ahn and Tao Zhu and Kornraphop Kawintiranon and Orhan Firat and Yiming Gu and Yujing Zhang and Matthew Rahtz and Manaal Faruqui and Natalie Clay and Justin Gilmer and JD Co-Reyes and Ivo Penchev and Rui Zhu and Nobuyuki Morioka and Kevin Hui and Krishna Haridasan and Victor Campos and Mahdis Mahdieh and Mandy Guo and Samer Hassan and Kevin Kilgour and Arpi Vezer and Heng-Tze Cheng and Raoul de Liedekerke and Siddharth Goyal and Paul Barham and DJ Strouse and Seb Noury and Jonas Adler and Mukund Sundararajan and Sharad Vikram and Dmitry Lepikhin and Michela Paganini and Xavier Garcia and Fan Yang and Dasha Valter and Maja Trebacz and Kiran Vodrahalli and Chulayuth Asawaroengchai and Roman Ring and Norbert Kalb and Livio Baldini Soares and Siddhartha Brahma and David Steiner and Tianhe Yu and Fabian Mentzer and Antoine He and Lucas Gonzalez and Bibo Xu and Raphael Lopez Kaufman and Laurent El Shafey and Junhyuk Oh and Tom Hennigan and George van den Driessche and Seth Odoom and Mario Lucic and Becca Roelofs and Sid Lall and Amit Marathe and Betty Chan and Santiago Ontanon and Luheng He and Denis Teplyashin and Jonathan Lai and Phil Crone and Bogdan Damoc and Lewis Ho and Sebastian Riedel and Karel Lenc and Chih-Kuan Yeh and Aakanksha Chowdhery and Yang Xu and Mehran Kazemi and Ehsan Amid and Anastasia Petrushkina and Kevin Swersky and Ali Khodaei and Gowoon Chen and Chris Larkin and Mario Pinto and Geng Yan and Adria Puigdomenech Badia and Piyush Patil and Steven Hansen and Dave Orr and Sebastien M. R. Arnold and Jordan Grimstad and Andrew Dai and Sholto Douglas and Rishika Sinha and Vikas Yadav and Xi Chen and Elena Gribovskaya and Jacob Austin and Jeffrey Zhao and Kaushal Patel and Paul Komarek and Sophia Austin and Sebastian Borgeaud and Linda Friso and Abhimanyu Goyal and Ben Caine and Kris Cao and Da-Woon Chung and Matthew Lamm and Gabe Barth-Maron and Thais Kagohara and Kate Olszewska and Mia Chen and Kaushik Shivakumar and Rishabh Agarwal and Harshal Godhia and Ravi Rajwar and Javier Snaider and Xerxes Dotiwalla and Yuan Liu and Aditya Barua and Victor Ungureanu and Yuan Zhang and Bat-Orgil Batsaikhan and Mateo Wirth and James Qin and Ivo Danihelka and Tulsee Doshi and Martin Chadwick and Jilin Chen and Sanil Jain and Quoc Le and Arjun Kar and Madhu Gurumurthy and Cheng Li and Ruoxin Sang and Fangyu Liu and Lampros Lamprou and Rich Munoz and Nathan Lintz and Harsh Mehta and Heidi Howard and Malcolm Reynolds and Lora Aroyo and Quan Wang and Lorenzo Blanco and Albin Cassirer and Jordan Griffith and Dipanjan Das and Stephan Lee and Jakub Sygnowski and Zach Fisher and James Besley and Richard Powell and Zafarali Ahmed and Dominik Paulus and David Reitter and Zalan Borsos and Rishabh Joshi and Aedan Pope and Steven Hand and Vittorio Selo and Vihan Jain and Nikhil Sethi and Megha Goel and Takaki Makino and Rhys May and Zhen Yang and Johan Schalkwyk and Christina Butterfield and Anja Hauth and Alex Goldin and Will Hawkins and Evan Senter and Sergey Brin and Oliver Woodman and Marvin Ritter and Eric Noland and Minh Giang and Vijay Bolina and Lisa Lee and Tim Blyth and Ian Mackinnon and Machel Reid and Obaid Sarvana and David Silver and Alexander Chen and Lily Wang and Loren Maggiore and Oscar Chang and Nithya Attaluri and Gregory Thornton and Chung-Cheng Chiu and Oskar Bunyan and Nir Levine and Timothy Chung and Evgenii Eltyshev and Xiance Si and Timothy Lillicrap and Demetra Brady and Vaibhav Aggarwal and Boxi Wu and Yuanzhong Xu and Ross McIlroy and Kartikeya Badola and Paramjit Sandhu and Erica Moreira and Wojciech Stokowiec and Ross Hemsley and Dong Li and Alex Tudor and Pranav Shyam and Elahe Rahimtoroghi and Salem Haykal and Pablo Sprechmann and Xiang Zhou and Diana Mincu and Yujia Li and Ravi Addanki and Kalpesh Krishna and Xiao Wu and Alexandre Frechette and Matan Eyal and Allan Dafoe and Dave Lacey and Jay Whang and Thi Avrahami and Ye Zhang and Emanuel Taropa and Hanzhao Lin and Daniel Toyama and Eliza Rutherford and Motoki Sano and HyunJeong Choe and Alex Tomala and Chalence Safranek-Shrader and Nora Kassner and Mantas Pajarskas and Matt Harvey and Sean Sechrist and Meire Fortunato and Christina Lyu and Gamaleldin Elsayed and Chenkai Kuang and James Lottes and Eric Chu and Chao Jia and Chih-Wei Chen and Peter Humphreys and Kate Baumli and Connie Tao and Rajkumar Samuel and Cicero Nogueira dos Santos and Anders Andreassen and Nemanja Rakićević and Dominik Grewe and Aviral Kumar and Stephanie Winkler and Jonathan Caton and Andrew Brock and Sid Dalmia and Hannah Sheahan and Iain Barr and Yingjie Miao and Paul Natsev and Jacob Devlin and Feryal Behbahani and Flavien Prost and Yanhua Sun and Artiom Myaskovsky and Thanumalayan Sankaranarayana Pillai and Dan Hurt and Angeliki Lazaridou and Xi Xiong and Ce Zheng and Fabio Pardo and Xiaowei Li and Dan Horgan and Joe Stanton and Moran Ambar and Fei Xia and Alejandro Lince and Mingqiu Wang and Basil Mustafa and Albert Webson and Hyo Lee and Rohan Anil and Martin Wicke and Timothy Dozat and Abhishek Sinha and Enrique Piqueras and Elahe Dabir and Shyam Upadhyay and Anudhyan Boral and Lisa Anne Hendricks and Corey Fry and Josip Djolonga and Yi Su and Jake Walker and Jane Labanowski and Ronny Huang and Vedant Misra and Jeremy Chen and RJ Skerry-Ryan and Avi Singh and Shruti Rijhwani and Dian Yu and Alex Castro-Ros and Beer Changpinyo and Romina Datta and Sumit Bagri and Arnar Mar Hrafnkelsson and Marcello Maggioni and Daniel Zheng and Yury Sulsky and Shaobo Hou and Tom Le Paine and Antoine Yang and Jason Riesa and Dominika Rogozinska and Dror Marcus and Dalia El Badawy and Qiao Zhang and Luyu Wang and Helen Miller and Jeremy Greer and Lars Lowe Sjos and Azade Nova and Heiga Zen and Rahma Chaabouni and Mihaela Rosca and Jiepu Jiang and Charlie Chen and Ruibo Liu and Tara Sainath and Maxim Krikun and Alex Polozov and Jean-Baptiste Lespiau and Josh Newlan and Zeyncep Cankara and Soo Kwak and Yunhan Xu and Phil Chen and Andy Coenen and Clemens Meyer and Katerina Tsihlas and Ada Ma and Juraj Gottweis and Jinwei Xing and Chenjie Gu and Jin Miao and Christian Frank and Zeynep Cankara and Sanjay Ganapathy and Ishita Dasgupta and Steph Hughes-Fitt and Heng Chen and David Reid and Keran Rong and Hongmin Fan and Joost van Amersfoort and Vincent Zhuang and Aaron Cohen and Shixiang Shane Gu and Anhad Mohananey and Anastasija Ilic and Taylor Tobin and John Wieting and Anna Bortsova and Phoebe Thacker and Emma Wang and Emily Caveness and Justin Chiu and Eren Sezener and Alex Kaskasoli and Steven Baker and Katie Millican and Mohamed Elhawaty and Kostas Aisopos and Carl Lebsack and Nathan Byrd and Hanjun Dai and Wenhao Jia and Matthew Wiethoff and Elnaz Davoodi and Albert Weston and Lakshman Yagati and Arun Ahuja and Isabel Gao and Golan Pundak and Susan Zhang and Michael Azzam and Khe Chai Sim and Sergi Caelles and James Keeling and Abhanshu Sharma and Andy Swing and YaGuang Li and Chenxi Liu and Carrie Grimes Bostock and Yamini Bansal and Zachary Nado and Ankesh Anand and Josh Lipschultz and Abhijit Karmarkar and Lev Proleev and Abe Ittycheriah and Soheil Hassas Yeganeh and George Polovets and Aleksandra Faust and Jiao Sun and Alban Rrustemi and Pen Li and Rakesh Shivanna and Jeremiah Liu and Chris Welty and Federico Lebron and Anirudh Baddepudi and Sebastian Krause and Emilio Parisotto and Radu Soricut and Zheng Xu and Dawn Bloxwich and Melvin Johnson and Behnam Neyshabur and Justin Mao-Jones and Renshen Wang and Vinay Ramasesh and Zaheer Abbas and Arthur Guez and Constant Segal and Duc Dung Nguyen and James Svensson and Le Hou and Sarah York and Kieran Milan and Sophie Bridgers and Wiktor Gworek and Marco Tagliasacchi and James Lee-Thorp and Michael Chang and Alexey Guseynov and Ale Jakse Hartman and Michael Kwong and Ruizhe Zhao and Sheleem Kashem and Elizabeth Cole and Antoine Miech and Richard Tanburn and Mary Phuong and Filip Pavetic and Sebastien Cevey and Ramona Comanescu and Richard Ives and Sherry Yang and Cosmo Du and Bo Li and Zizhao Zhang and Mariko Iinuma and Clara Huiyi Hu and Aurko Roy and Shaan Bijwadia and Zhenkai Zhu and Danilo Martins and Rachel Saputro and Anita Gergely and Steven Zheng and Dawei Jia and Ioannis Antonoglou and Adam Sadovsky and Shane Gu and Yingying Bi and Alek Andreev and Sina Samangooei and Mina Khan and Tomas Kocisky and Angelos Filos and Chintu Kumar and Colton Bishop and Adams Yu and Sarah Hodkinson and Sid Mittal and Premal Shah and Alexandre Moufarek and Yong Cheng and Adam Bloniarz and Jaehoon Lee and Pedram Pejman and Paul Michel and Stephen Spencer and Vladimir Feinberg and Xuehan Xiong and Nikolay Savinov and Charlotte Smith and Siamak Shakeri and Dustin Tran and Mary Chesus and Bernd Bohnet and George Tucker and Tamara von Glehn and Carrie Muir and Yiran Mao and Hideto Kazawa and Ambrose Slone and Kedar Soparkar and Disha Shrivastava and James Cobon-Kerr and Michael Sharman and Jay Pavagadhi and Carlos Araya and Karolis Misiunas and Nimesh Ghelani and Michael Laskin and David Barker and Qiujia Li and Anton Briukhov and Neil Houlsby and Mia Glaese and Balaji Lakshminarayanan and Nathan Schucher and Yunhao Tang and Eli Collins and Hyeontaek Lim and Fangxiaoyu Feng and Adria Recasens and Guangda Lai and Alberto Magni and Nicola De Cao and Aditya Siddhant and Zoe Ashwood and Jordi Orbay and Mostafa Dehghani and Jenny Brennan and Yifan He and Kelvin Xu and Yang Gao and Carl Saroufim and James Molloy and Xinyi Wu and Seb Arnold and Solomon Chang and Julian Schrittwieser and Elena Buchatskaya and Soroush Radpour and Martin Polacek and Skye Giordano and Ankur Bapna and Simon Tokumine and Vincent Hellendoorn and Thibault Sottiaux and Sarah Cogan and Aliaksei Severyn and Mohammad Saleh and Shantanu Thakoor and Laurent Shefey and Siyuan Qiao and Meenu Gaba and Shuo-yiin Chang and Craig Swanson and Biao Zhang and Benjamin Lee and Paul Kishan Rubenstein and Gan Song and Tom Kwiatkowski and Anna Koop and Ajay Kannan and David Kao and Parker Schuh and Axel Stjerngren and Golnaz Ghiasi and Gena Gibson and Luke Vilnis and Ye Yuan and Felipe Tiengo Ferreira and Aishwarya Kamath and Ted Klimenko and Ken Franko and Kefan Xiao and Indro Bhattacharya and Miteyan Patel and Rui Wang and Alex Morris and Robin Strudel and Vivek Sharma and Peter Choy and Sayed Hadi Hashemi and Jessica Landon and Mara Finkelstein and Priya Jhakra and Justin Frye and Megan Barnes and Matthew Mauger and Dennis Daun and Khuslen Baatarsukh and Matthew Tung and Wael Farhan and Henryk Michalewski and Fabio Viola and Felix de Chaumont Quitry and Charline Le Lan and Tom Hudson and Qingze Wang and Felix Fischer and Ivy Zheng and Elspeth White and Anca Dragan and Jean-baptiste Alayrac and Eric Ni and Alexander Pritzel and Adam Iwanicki and Michael Isard and Anna Bulanova and Lukas Zilka and Ethan Dyer and Devendra Sachan and Srivatsan Srinivasan and Hannah Muckenhirn and Honglong Cai and Amol Mandhane and Mukarram Tariq and Jack W. Rae and Gary Wang and Kareem Ayoub and Nicholas FitzGerald and Yao Zhao and Woohyun Han and Chris Alberti and Dan Garrette and Kashyap Krishnakumar and Mai Gimenez and Anselm Levskaya and Daniel Sohn and Josip Matak and Inaki Iturrate and Michael B. Chang and Jackie Xiang and Yuan Cao and Nishant Ranka and Geoff Brown and Adrian Hutter and Vahab Mirrokni and Nanxin Chen and Kaisheng Yao and Zoltan Egyed and Francois Galilee and Tyler Liechty and Praveen Kallakuri and Evan Palmer and Sanjay Ghemawat and Jasmine Liu and David Tao and Chloe Thornton and Tim Green and Mimi Jasarevic and Sharon Lin and Victor Cotruta and Yi-Xuan Tan and Noah Fiedel and Hongkun Yu and Ed Chi and Alexander Neitz and Jens Heitkaemper and Anu Sinha and Denny Zhou and Yi Sun and Charbel Kaed and Brice Hulse and Swaroop Mishra and Maria Georgaki and Sneha Kudugunta and Clement Farabet and Izhak Shafran and Daniel Vlasic and Anton Tsitsulin and Rajagopal Ananthanarayanan and Alen Carin and Guolong Su and Pei Sun and Shashank V and Gabriel Carvajal and Josef Broder and Iulia Comsa and Alena Repina and William Wong and Warren Weilun Chen and Peter Hawkins and Egor Filonov and Lucia Loher and Christoph Hirnschall and Weiyi Wang and Jingchen Ye and Andrea Burns and Hardie Cate and Diana Gage Wright and Federico Piccinini and Lei Zhang and Chu-Cheng Lin and Ionel Gog and Yana Kulizhskaya and Ashwin Sreevatsa and Shuang Song and Luis C. Cobo and Anand Iyer and Chetan Tekur and Guillermo Garrido and Zhuyun Xiao and Rupert Kemp and Huaixiu Steven Zheng and Hui Li and Ananth Agarwal and Christel Ngani and Kati Goshvadi and Rebeca Santamaria-Fernandez and Wojciech Fica and Xinyun Chen and Chris Gorgolewski and Sean Sun and Roopal Garg and Xinyu Ye and S. M. Ali Eslami and Nan Hua and Jon Simon and Pratik Joshi and Yelin Kim and Ian Tenney and Sahitya Potluri and Lam Nguyen Thiet and Quan Yuan and Florian Luisier and Alexandra Chronopoulou and Salvatore Scellato and Praveen Srinivasan and Minmin Chen and Vinod Koverkathu and Valentin Dalibard and Yaming Xu and Brennan Saeta and Keith Anderson and Thibault Sellam and Nick Fernando and Fantine Huot and Junehyuk Jung and Mani Varadarajan and Michael Quinn and Amit Raul and Maigo Le and Ruslan Habalov and Jon Clark and Komal Jalan and Kalesha Bullard and Achintya Singhal and Thang Luong and Boyu Wang and Sujeevan Rajayogam and Julian Eisenschlos and Johnson Jia and Daniel Finchelstein and Alex Yakubovich and Daniel Balle and Michael Fink and Sameer Agarwal and Jing Li and Dj Dvijotham and Shalini Pal and Kai Kang and Jaclyn Konzelmann and Jennifer Beattie and Olivier Dousse and Diane Wu and Remi Crocker and Chen Elkind and Siddhartha Reddy Jonnalagadda and Jong Lee and Dan Holtmann-Rice and Krystal Kallarackal and Rosanne Liu and Denis Vnukov and Neera Vats and Luca Invernizzi and Mohsen Jafari and Huanjie Zhou and Lilly Taylor and Jennifer Prendki and Marcus Wu and Tom Eccles and Tianqi Liu and Kavya Kopparapu and Francoise Beaufays and Christof Angermueller and Andreea Marzoca and Shourya Sarcar and Hilal Dib and Jeff Stanway and Frank Perbet and Nejc Trdin and Rachel Sterneck and Andrey Khorlin and Dinghua Li and Xihui Wu and Sonam Goenka and David Madras and Sasha Goldshtein and Willi Gierke and Tong Zhou and Yaxin Liu and Yannie Liang and Anais White and Yunjie Li and Shreya Singh and Sanaz Bahargam and Mark Epstein and Sujoy Basu and Li Lao and Adnan Ozturel and Carl Crous and Alex Zhai and Han Lu and Zora Tung and Neeraj Gaur and Alanna Walton and Lucas Dixon and Ming Zhang and Amir Globerson and Grant Uy and Andrew Bolt and Olivia Wiles and Milad Nasr and Ilia Shumailov and Marco Selvi and Francesco Piccinno and Ricardo Aguilar and Sara McCarthy and Misha Khalman and Mrinal Shukla and Vlado Galic and John Carpenter and Kevin Villela and Haibin Zhang and Harry Richardson and James Martens and Matko Bosnjak and Shreyas Rammohan Belle and Jeff Seibert and Mahmoud Alnahlawi and Brian McWilliams and Sankalp Singh and Annie Louis and Wen Ding and Dan Popovici and Lenin Simicich and Laura Knight and Pulkit Mehta and Nishesh Gupta and Chongyang Shi and Saaber Fatehi and Jovana Mitrovic and Alex Grills and Joseph Pagadora and Tsendsuren Munkhdalai and Dessie Petrova and Danielle Eisenbud and Zhishuai Zhang and Damion Yates and Bhavishya Mittal and Nilesh Tripuraneni and Yannis Assael and Thomas Brovelli and Prateek Jain and Mihajlo Velimirovic and Canfer Akbulut and Jiaqi Mu and Wolfgang Macherey and Ravin Kumar and Jun Xu and Haroon Qureshi and Gheorghe Comanici and Jeremy Wiesner and Zhitao Gong and Anton Ruddock and Matthias Bauer and Nick Felt and Anirudh GP and Anurag Arnab and Dustin Zelle and Jonas Rothfuss and Bill Rosgen and Ashish Shenoy and Bryan Seybold and Xinjian Li and Jayaram Mudigonda and Goker Erdogan and Jiawei Xia and Jiri Simsa and Andrea Michi and Yi Yao and Christopher Yew and Steven Kan and Isaac Caswell and Carey Radebaugh and Andre Elisseeff and Pedro Valenzuela and Kay McKinney and Kim Paterson and Albert Cui and Eri Latorre-Chimoto and Solomon Kim and William Zeng and Ken Durden and Priya Ponnapalli and Tiberiu Sosea and Christopher A. Choquette-Choo and James Manyika and Brona Robenek and Harsha Vashisht and Sebastien Pereira and Hoi Lam and Marko Velic and Denese Owusu-Afriyie and Katherine Lee and Tolga Bolukbasi and Alicia Parrish and Shawn Lu and Jane Park and Balaji Venkatraman and Alice Talbert and Lambert Rosique and Yuchung Cheng and Andrei Sozanschi and Adam Paszke and Praveen Kumar and Jessica Austin and Lu Li and Khalid Salama and Bartek Perz and Wooyeol Kim and Nandita Dukkipati and Anthony Baryshnikov and Christos Kaplanis and XiangHai Sheng and Yuri Chervonyi and Caglar Unlu and Diego de Las Casas and Harry Askham and Kathryn Tunyasuvunakool and Felix Gimeno and Siim Poder and Chester Kwak and Matt Miecnikowski and Vahab Mirrokni and Alek Dimitriev and Aaron Parisi and Dangyi Liu and Tomy Tsai and Toby Shevlane and Christina Kouridi and Drew Garmon and Adrian Goedeckemeyer and Adam R. Brown and Anitha Vijayakumar and Ali Elqursh and Sadegh Jazayeri and Jin Huang and Sara Mc Carthy and Jay Hoover and Lucy Kim and Sandeep Kumar and Wei Chen and Courtney Biles and Garrett Bingham and Evan Rosen and Lisa Wang and Qijun Tan and David Engel and Francesco Pongetti and Dario de Cesare and Dongseong Hwang and Lily Yu and Jennifer Pullman and Srini Narayanan and Kyle Levin and Siddharth Gopal and Megan Li and Asaf Aharoni and Trieu Trinh and Jessica Lo and Norman Casagrande and Roopali Vij and Loic Matthey and Bramandia Ramadhana and Austin Matthews and CJ Carey and Matthew Johnson and Kremena Goranova and Rohin Shah and Shereen Ashraf and Kingshuk Dasgupta and Rasmus Larsen and Yicheng Wang and Manish Reddy Vuyyuru and Chong Jiang and Joana Ijazi and Kazuki Osawa and Celine Smith and Ramya Sree Boppana and Taylan Bilal and Yuma Koizumi and Ying Xu and Yasemin Altun and Nir Shabat and Ben Bariach and Alex Korchemniy and Kiam Choo and Olaf Ronneberger and Chimezie Iwuanyanwu and Shubin Zhao and David Soergel and Cho-Jui Hsieh and Irene Cai and Shariq Iqbal and Martin Sundermeyer and Zhe Chen and Elie Bursztein and Chaitanya Malaviya and Fadi Biadsy and Prakash Shroff and Inderjit Dhillon and Tejasi Latkar and Chris Dyer and Hannah Forbes and Massimo Nicosia and Vitaly Nikolaev and Somer Greene and Marin Georgiev and Pidong Wang and Nina Martin and Hanie Sedghi and John Zhang and Praseem Banzal and Doug Fritz and Vikram Rao and Xuezhi Wang and Jiageng Zhang and Viorica Patraucean and Dayou Du and Igor Mordatch and Ivan Jurin and Lewis Liu and Ayush Dubey and Abhi Mohan and Janek Nowakowski and Vlad-Doru Ion and Nan Wei and Reiko Tojo and Maria Abi Raad and Drew A. Hudson and Vaishakh Keshava and Shubham Agrawal and Kevin Ramirez and Zhichun Wu and Hoang Nguyen and Ji Liu and Madhavi Sewak and Bryce Petrini and DongHyun Choi and Ivan Philips and Ziyue Wang and Ioana Bica and Ankush Garg and Jarek Wilkiewicz and Priyanka Agrawal and Xiaowei Li and Danhao Guo and Emily Xue and Naseer Shaik and Andrew Leach and Sadh MNM Khan and Julia Wiesinger and Sammy Jerome and Abhishek Chakladar and Alek Wenjiao Wang and Tina Ornduff and Folake Abu and Alireza Ghaffarkhah and Marcus Wainwright and Mario Cortes and Frederick Liu and Joshua Maynez and Andreas Terzis and Pouya Samangouei and Riham Mansour and Tomasz Kępa and François-Xavier Aubet and Anton Algymr and Dan Banica and Agoston Weisz and Andras Orban and Alexandre Senges and Ewa Andrejczuk and Mark Geller and Niccolo Dal Santo and Valentin Anklin and Majd Al Merey and Martin Baeuml and Trevor Strohman and Junwen Bai and Slav Petrov and Yonghui Wu and Demis Hassabis and Koray Kavukcuoglu and Jeff Dean and Oriol Vinyals}, year = {2024}, eprint = {2403.05530}, archiveprefix = {arXiv} } @misc{gen4u2026, title = {Gen4U: Unifying Video Generation and Understanding via Diffusion}, author = {Michael King and Aravindh Mahendran and Matthew Koichi Grimes and Fedor Kitashov and Adham Elarabawy and Pedro Velez and Maks Ovsjanikov and Viorica Pătrăucean}, year = {2026}, eprint = {2607.06856}, archiveprefix = {arXiv} } @inproceedings{koh2023gill, title = {Generating Images with Multimodal Language Models}, author = {Jing Yu Koh and Daniel Fried and Ruslan Salakhutdinov}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {21487--21506}, doi = {10.52202/075280-0939} } @article{goodfellow2020generative, title = {Generative Adversarial Networks}, author = {Goodfellow, Ian and Pouget-Abadie, Jean and Mirza, Mehdi and Xu, Bing and Warde-Farley, David and Ozair, Sherjil and Courville, Aaron and Bengio, Yoshua}, journal = {Communications of the ACM}, year = {2020}, volume = {63}, number = {11}, pages = {139--144}, doi = {10.1145/3422622} } @inproceedings{sun2024emu2, title = {Generative Multimodal Models Are In-Context Learners}, author = {Sun, Quan and Cui, Yufeng and Zhang, Xiaosong and Zhang, Fan and Yu, Qiying and Wang, Yueze and Rao, Yongming and Liu, Jingjing and Huang, Tiejun and Wang, Xinlong}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {14398--14409}, doi = {10.1109/cvpr52733.2024.01365} } @misc{genie2_2024, title = {Genie 2: A Large-Scale Foundation World Model}, author = {Jack Parker-Holder and Philip Ball and Jake Bruce and Vibhavari Dasagi and Kristian Holsheimer and Christos Kaplanis and Alexandre Moufarek and Guy Scully and Jeremy Shar and Jimmy Shi and Stephen Spencer and Jessica Yung and Michael Dennis and Sultan Kenjeyev and Shangbang Long and Vlad Mnih and Harris Chan and Maxime Gazeau and Bonnie Li and Fabio Pardo and Luyu Wang and Lei Zhang and Frederic Besse and Tim Harley and Anna Mitenkova and Jane Wang and Jeff Clune and Demis Hassabis and Raia Hadsell and Adrian Bolton and Satinder Singh and Tim Rockt{\"a}schel}, year = {2024}, howpublished = {Google DeepMind publication} } @misc{genie3_2025, title = {Genie 3: A New Frontier for World Models}, author = {Parker-Holder, Jack and Fruchter, Shlomi}, year = {2025}, howpublished = {Google DeepMind publication} } @inproceedings{bruce2024genie, title = {Genie: Generative Interactive Environments}, author = {Jake Bruce and Michael Dennis and Ashley Edwards and Jack Parker-Holder and Yuge Shi and Edward Hughes and Matthew Lai and Aditi Mavalankar and Richie Steigerwald and Chris Apps and Yusuf Aytar and Sarah Bechtle and Feryal Behbahani and Stephanie Chan and Nicolas Heess and Lucy Gonzalez and Simon Osindero and Sherjil Ozair and Scott Reed and Jingwei Zhang and Konrad Zolna and Jeff Clune and de Freitas, Nando and Satinder Singh and Tim Rockt\"{a}schel}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {4603--4623}, } @misc{wei2026gimworld, title = {Geometry-Aware Implicit Memory for Video World Models}, author = {Zhengxuan Wei and Xu Guo and Xinghui Li and Xunzhi Xiang and Min Wei and Yiran Zhu and Qiulin Wang and Xintao Wang and Pengfei Wan and Xiangwang Hou and Qi Fan}, year = {2026}, eprint = {2606.02436}, archiveprefix = {arXiv} } @misc{gigaworld2025, title = {GigaWorld-0: World Models As Data Engine to Empower Embodied AI}, author = {GigaWorld Team and Angen Ye and Boyuan Wang and Chaojun Ni and Guan Huang and Guosheng Zhao and Haoyun Li and Jiagang Zhu and Kerui Li and Mengyuan Xu and Qiuping Deng and Siting Wang and Wenkang Qin and Xinze Chen and Xiaofeng Wang and Yankai Wang and Yu Cao and Yifan Chang and Yuan Xu and Yun Ye and Yang Wang and Yukun Zhou and Zhengyuan Zhang and Zhehao Dong and Zheng Zhu}, year = {2025}, eprint = {2511.19861}, archiveprefix = {arXiv} } @misc{gigaworldteam2026gigaworld1, title = {{GigaWorld-1}: A Roadmap to Build World Models for Robot Policy Evaluation}, author = {{GigaWorld Team} and Ma, Angyuan and Wang, Boyuan and Li, Bohan and Ni, Chaojun and Li, Guo and Huang, Guan and Zhao, Guosheng and Li, Hao and Li, Hengtao and Liu, Jingyu and Lu, Jiwen and Deng, Qiuping and Yu, Tingdong and Xu, Xuancheng and Zhou, Xinyu and Xu, Xiuwei and Chen, Xinze and Wang, Xiaofeng and Tian, Xiaoyu and Wang, Yang and Chang, Yifan and Zhou, Yukun and Ye, Yun and Wu, Zhenyu and Wu, Zhanqian and Zhu, Zheng}, year = {2026}, eprint = {2607.02642}, archiveprefix = {arXiv} } @article{wang2022git, title = {{GIT}: A Generative Image-to-Text Transformer for Vision and Language}, author = {Jianfeng Wang and Zhengyuan Yang and Xiaowei Hu and Linjie Li and Kevin Lin and Zhe Gan and Zicheng Liu and Ce Liu and Lijuan Wang}, journal = {Transactions on Machine Learning Research}, year = {2022}, issn = {2835-8856} } @inproceedings{goku2025, title = {Goku: Flow Based Video Generative Foundation Models}, author = {Chen, Shoufa and Ge, Chongjian and Zhang, Yuqi and Zhang, Yida and Zhu, Fengda and Yang, Hao and Hao, Hongxiang and Wu, Hui and Lai, Zhichao and Hu, Yifei and Lin, Ting-Che and Zhang, Shilong and Li, Fu and Li, Chuan and Wang, Xing and Peng, Yanghua and Sun, Peize and Luo, Ping and Jiang, Yi and Yuan, Zehuan and Peng, Bingyue and Liu, Xiaobing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {23516--23527}, doi = {10.1109/cvpr52734.2025.02190} } @inproceedings{wang2023gpt4video, title = {{GPT4Video}: A Unified Multimodal Large Language Model for Instruction-Followed Understanding and Safety-Aware Generation}, author = {Wang, Zhanyu and Wang, Longyue and Zhao, Zhen and Wu, Minghao and Lyu, Chenyang and Li, Huayang and Cai, Deng and Zhou, Luping and Shi, Shuming and Tu, Zhaopeng}, booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia}, year = {2024}, pages = {3907--3916}, doi = {10.1145/3664647.3681464} } @inproceedings{chen2025grpocare, title = {{GRPO}-{CARE}: Consistency-Aware Reinforcement Learning for Multimodal Reasoning}, author = {Chen, Yi and Ge, Yuying and Wang, Rui and Ge, Yixiao and Cheng, Junhao and Shan, Ying and Liu, Xihui}, booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026}, year = {2026}, pages = {4305--4320}, doi = {10.18653/v1/2026.findings-acl.210}, } @misc{zhang2026hjepa, title = {{H-JEPA}: End-to-End Learning of Hierarchical World Models for Visual Planning}, author = {Zhang, Wancong and Terver, Basile and Rabbat, Michael and LeCun, Yann and Balestriero, Randall}, year = {2026}, eprint = {2610.06805}, archiveprefix = {arXiv} } @misc{xu2024hallo, title = {Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation}, author = {Mingwang Xu and Hui Li and Qingkun Su and Hanlin Shang and Liwei Zhang and Ce Liu and Jingdong Wang and Yao Yao and Siyu Zhu}, year = {2024}, eprint = {2406.08801}, archiveprefix = {arXiv} } @misc{xiao2025haploomni, title = {HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation}, author = {Yicheng Xiao and Lin Song and Rui Yang and Cheng Cheng and Zunnan Xu and Zhaoyang Zhang and Yixiao Ge and Xiu Li and Ying Shan}, year = {2025}, eprint = {2506.02975}, archiveprefix = {arXiv} } @inproceedings{perrett2025hdepic, title = {HD-EPIC: A Highly-Detailed Egocentric Video Dataset}, author = {Perrett, Toby and Darkhalil, Ahmad and Sinha, Saptarshi and Emara, Omar and Pollard, Sam and Parida, Kranti Kumar and Liu, Kaiting and Gatti, Prajwal and Bansal, Siddhant and Flanagan, Kevin and Chalk, Jacob and Zhu, Zhifan and Guerrier, Rhodri and Abdelazim, Fahd and Zhu, Bin and Moltisanti, Davide and Wray, Michael and Doughty, Hazel and Damen, Dima}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {23901--23913}, doi = {10.1109/cvpr52734.2025.02226} } @inproceedings{rombach2022high, title = {High-Resolution Image Synthesis with Latent Diffusion Models}, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bjorn}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {10684--10695}, doi = {10.1109/cvpr52688.2022.01042} } @inproceedings{zhou2025hitvideo, title = {HiTVideo: Hierarchical Tokenizers for Enhancing Text-to-Video Generation with Autoregressive Large Language Models}, author = {Zhou, Ziqin and Yang, Yifan and Yang, Yuqing and He, Tianyu and Peng, Houwen and Qiu, Kai and Dai, Qi and Qiu, Lili and Luo, Chong and Liu, Lingqiao}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2026}, volume = {40}, number = {16}, pages = {13898--13906}, doi = {10.1609/aaai.v40i16.38399} } @inproceedings{kuehne2011hmdb, title = {HMDB: A Large Video Database for Human Motion Recognition}, author = {Kuehne, H. and Jhuang, H. and Garrote, E. and Poggio, T. and Serre, T.}, booktitle = {2011 International conference on computer vision}, year = {2011}, pages = {2556--2563}, doi = {10.1109/iccv.2011.6126543} } @inproceedings{cha2023honeybee, title = {Honeybee: Locality-Enhanced Projector for Multimodal LLM}, author = {Cha, Junbum and Kang, Wooyoung and Mun, Jonghwan and Roh, Byungseok}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {13817--13827}, } @misc{shi2026honeycomb, title = {Honeycomb: Constant-Size Scene Memory Representation for Video World Models}, author = {Jack Wei Lun Shi and Kaichen Zhou and Haoyu Chen and Yufeng Weng and Keane Ong and Ruojin Cai and Hang Hua and Justin K. W. Yeoh and Mengyu Wang}, year = {2026}, eprint = {2609.37690}, archiveprefix = {arXiv} } @inproceedings{cohen2026horizon, title = {Horizon Imagination: Efficient On-Policy Rollout in Diffusion World Models}, author = {Lior Cohen and Ofir Nabati and Kaixin Wang and Navdeep Kumar and Shie Mannor}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{chandrasegaran2024hourvideo, title = {HourVideo: 1-Hour Video-Language Understanding}, author = {Chandrasegaran, Keshigeyan and Gupta, Agrim and Hadzic, Lea M. and Kota, Taran and He, Jimming and Eyzaguirre, Cristobal and Durante, Zane and Li, Manling and Wu, Jiajun and Fei-Fei, Li}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {53168--53197}, doi = {10.52202/079017-1684} } @misc{yu2026worldmodeleval, title = {How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position}, author = {Yang Yu and Shiyuan Zhang and Yifei Sheng and Haoxiang Ren and Haoxin Lin}, year = {2026}, eprint = {2606.15032}, archiveprefix = {arXiv}, } @inproceedings{Miech_2019_ICCV, title = {HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips}, author = {Miech, Antoine and Zhukov, Dimitri and Alayrac, Jean-Baptiste and Tapaswi, Makarand and Laptev, Ivan and Sivic, Josef}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2019}, pages = {2630--2640}, doi = {10.1109/iccv.2019.00272} } @misc{gamecraft2025, title = {Hunyuan-GameCraft: High-Dynamic Interactive Game Video Generation with Hybrid History Condition}, author = {Jiaqi Li and Junshu Tang and Zhiyong Xu and Longhuang Wu and Yuan Zhou and Shuai Shao and Tianbao Yu and Zhiguo Cao and Qinglin Lu}, year = {2025}, eprint = {2506.17201}, archiveprefix = {arXiv} } @misc{wu2025hunyuan15, title = {{HunyuanVideo 1.5} Technical Report}, author = {Bing Wu and Chang Zou and Changlin Li and Duojun Huang and Fang Yang and Hao Tan and Jack Peng and Jianbing Wu and Jiangfeng Xiong and Jie Jiang and Linus and Patrol and Peizhen Zhang and Peng Chen and Penghao Zhao and Qi Tian and Songtao Liu and Weijie Kong and Weiyan Wang and Xiao He and Xin Li and Xinchi Deng and Xuefei Zhe and Yang Li and Yanxin Long and Yuanbo Peng and Yue Wu and Yuhong Liu and Zhenyu Wang and Zuozhuo Dai and Bo Peng and Coopers Li and Gu Gong and Guojian Xiao and Jiahe Tian and Jiaxin Lin and Jie Liu and Jihong Zhang and Jiesong Lian and Kaihang Pan and Lei Wang and Lin Niu and Mingtao Chen and Mingyang Chen and Mingzhe Zheng and Miles Yang and Qiangqiang Hu and Qi Yang and Qiuyong Xiao and Runzhou Wu and Ryan Xu and Rui Yuan and Shanshan Sang and Shisheng Huang and Siruis Gong and Shuo Huang and Weiting Guo and Xiang Yuan and Xiaojia Chen and Xiawei Hu and Wenzhi Sun and Xiele Wu and Xianshun Ren and Xiaoyan Yuan and Xiaoyue Mi and Yepeng Zhang and Yifu Sun and Yiting Lu and Yitong Li and You Huang and Yu Tang and Yixuan Li and Yuhang Deng and Yuan Zhou and Zhichao Hu and Zhiguang Liu and Zhihe Yang and Zilin Yang and Zhenzhi Lu and Zixiang Zhou and Zhao Zhong}, year = {2025}, eprint = {2511.18870}, archiveprefix = {arXiv} } @misc{hunyuanvideo2024, title = {HunyuanVideo: A Systematic Framework for Large Video Generative Models}, author = {Weijie Kong and Qi Tian and Zijian Zhang and Rox Min and Zuozhuo Dai and Jin Zhou and Jiangfeng Xiong and Xin Li and Bo Wu and Jianwei Zhang and Kathrina Wu and Qin Lin and Junkun Yuan and Yanxin Long and Aladdin Wang and Andong Wang and Changlin Li and Duojun Huang and Fang Yang and Hao Tan and Hongmei Wang and Jacob Song and Jiawang Bai and Jianbing Wu and Jinbao Xue and Joey Wang and Kai Wang and Mengyang Liu and Pengyu Li and Shuai Li and Weiyan Wang and Wenqing Yu and Xinchi Deng and Yang Li and Yi Chen and Yutao Cui and Yuanbo Peng and Zhentao Yu and Zhiyu He and Zhiyong Xu and Zixiang Zhou and Zunnan Xu and Yangyu Tao and Qinglin Lu and Songtao Liu and Dax Zhou and Hongfa Wang and Yong Yang and Di Wang and Yuhong Liu and Jie Jiang and Caesar Zhong}, year = {2024}, eprint = {2412.03603}, archiveprefix = {arXiv} } @misc{hydrax2026, title = {HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers}, author = {Guozhen Zhang and Xuerui Qiu and Yutao Cui and Tianhui Song and Changlin Li and Junzhe Li and Tao Huang and Xiao Zhang and Yang Li and Jianbing Wu and Miles Yang and Zhao Zhong and Liefeng Bo and Limin Wang}, year = {2026}, eprint = {2606.13289}, archiveprefix = {arXiv} } @inproceedings{yuan2024consisid, title = {Identity-Preserving Text-to-Video Generation by Frequency Decomposition}, author = {Yuan, Shenghai and Huang, Jinfa and He, Xianyi and Ge, Yunyang and Shi, Yujun and Chen, Liuhan and Luo, Jiebo and Yuan, Li}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {12978--12988}, doi = {10.1109/cvpr52734.2025.01211} } @misc{chen2024igor, title = {IGOR: Image-GOal Representations Are the Atomic Control Units for Foundation Models in Embodied AI}, author = {Xiaoyu Chen and Junliang Guo and Tianyu He and Chuheng Zhang and Pushi Zhang and Derek Cathera Yang and Li Zhao and Jiang Bian}, year = {2024}, eprint = {2411.00785}, archiveprefix = {arXiv} } @inproceedings{zhao2024bsq, title = {Image and Video Tokenization with Binary Spherical Quantization}, author = {Zhao, Yue and Xiong, Yuanjun and Krähenbühl, Philipp}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @article{wang2004ssim, title = {Image Quality Assessment: From Error Visibility to Structural Similarity}, author = {Zhou Wang and Alan C. Bovik and Hamid R. Sheikh and Eero P. Simoncelli}, journal = {IEEE Transactions on Image Processing}, year = {2004}, volume = {13}, number = {4}, pages = {600--612}, doi = {10.1109/TIP.2003.819861} } @misc{ho2022imagen, title = {Imagen Video: High Definition Video Generation with Diffusion Models}, author = {Jonathan Ho and William Chan and Chitwan Saharia and Jay Whang and Ruiqi Gao and Alexey Gritsenko and Diederik P. Kingma and Ben Poole and Mohammad Norouzi and David J. Fleet and Tim Salimans}, year = {2022}, eprint = {2210.02303}, archiveprefix = {arXiv} } @inproceedings{salimans2016improved, title = {Improved Techniques for Training GANs}, author = {Salimans, Tim and Goodfellow, Ian and Zaremba, Wojciech and Cheung, Vicki and Radford, Alec and Chen, Xi}, booktitle = {Advances in Neural Information Processing Systems}, year = {2016}, volume = {29}, } @inproceedings{liu2025videoreward, title = {Improving Video Generation with Human Feedback}, author = {Liu, Jie and Liu, Gongye and Liang, Jiajun and Yuan, Ziyang and Liu, Xiaokun and Zheng, Mingwu and Wu, Xiele and Wang, Qiulin and Xia, Menghan and Wang, Xintao and Liu, Xiaohong and Yang, Fei and Wan, Pengfei and ZHANG, Di and Gai, Kun and Yang, Yujiu and Ouyang, Wanli}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {82155--82192}, doi = {10.52202/085713-2750} } @inproceedings{infinitystar2025, title = {InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation}, author = {Liu, Jinlai and Han, Jian and Yan, Bin and Wu, Hui and Zhu, Fengda and Wang, Xing and Jiang, Yi and PENG, BINGYUE and Yuan, Zehuan}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {170054--170072}, doi = {10.52202/085713-5660} } @inproceedings{wang2023internvid, title = {InternVid: A Large-Scale Video-Text Dataset for Multimodal Understanding and Generation}, author = {Wang, Yi and He, Yinan and Li, Yizhuo and Li, Kunchang and Yu, Jiashuo and Ma, Xin and Li, Xinhao and Chen, Guo and Chen, Xinyuan and Wang, Yaohui and He, Conghui and Luo, Ping and Liu, Ziwei and Wang, Yali and Wang, Limin and Qiao, Yu}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{wang2025internvideonext, title = {InternVideo-Next: Towards World-Understanding Video Models}, author = {Wang, Chenting and Zhu, Yuhan and Xu, Yicheng and Yang, Jiange and Yan, Ziang and Wang, Yali and Wang, Yi and Wang, Limin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {16966--16976}, } @inproceedings{wang2024internvideo2, title = {InternVideo2: Scaling Foundation Models for Multimodal Video Understanding}, author = {Yi Wang and Kunchang Li and Xinhao Li and Jiashuo Yu and Yinan He and Guo Chen and Baoqi Pei and Rongkun Zheng and Zun Wang and Yansong Shi and Tianxiang Jiang and Songze Li and Jilan Xu and Hongjie Zhang and Yifei Huang and Yu Qiao and Yali Wang and Limin Wang}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, pages = {396--416}, doi = {10.1007/978-3-031-73013-9_23} } @misc{yan2026internvideo3, title = {InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning}, author = {Ziang Yan and Sheng Xia and Jiashuo Yu and Yue Wu and Tianxiang Jiang and Songze Li and Kanghui Tian and Yicheng Xu and Yinan He and Kai Chen and Limin Wang and Yu Qiao and Yi Wang}, year = {2026}, eprint = {2606.12195}, archiveprefix = {arXiv} } @misc{wang2022internvideo, title = {InternVideo: General Video Foundation Models via Generative and Discriminative Learning}, author = {Yi Wang and Kunchang Li and Yizhuo Li and Yinan He and Bingkun Huang and Zhiyu Zhao and Hongjie Zhang and Jilan Xu and Yi Liu and Zun Wang and Sen Xing and Guo Chen and Junting Pan and Jiashuo Yu and Yali Wang and Limin Wang and Yu Qiao}, year = {2022}, eprint = {2212.03191}, archiveprefix = {arXiv} } @misc{wang2025internvl3, title = {InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency}, author = {Weiyun Wang and Zhangwei Gao and Lixin Gu and Hengjun Pu and Long Cui and Xingguang Wei and Zhaoyang Liu and Linglin Jing and Shenglong Ye and Jie Shao and Zhaokai Wang and Zhe Chen and Hongjie Zhang and Ganlin Yang and Haomin Wang and Qi Wei and Jinhui Yin and Wenhao Li and Erfei Cui and Guanzhou Chen and Zichen Ding and Changyao Tian and Zhenyu Wu and Jingjing Xie and Zehao Li and Bowen Yang and Yuchen Duan and Xuehui Wang and Zhi Hou and Haoran Hao and Tianyi Zhang and Songze Li and Xiangyu Zhao and Haodong Duan and Nianchen Deng and Bin Fu and Yinan He and Yi Wang and Conghui He and Botian Shi and Junjun He and Yingtong Xiong and Han Lv and Lijun Wu and Wenqi Shao and Kaipeng Zhang and Huipeng Deng and Biqing Qi and Jiaye Ge and Qipeng Guo and Wenwei Zhang and Songyang Zhang and Maosong Cao and Junyao Lin and Kexian Tang and Jianfei Gao and Haian Huang and Yuzhe Gu and Chengqi Lyu and Huanze Tang and Rui Wang and Haijun Lv and Wanli Ouyang and Limin Wang and Min Dou and Xizhou Zhu and Tong Lu and Dahua Lin and Jifeng Dai and Weijie Su and Bowen Zhou and Kai Chen and Yu Qiao and Wenhai Wang and Gen Luo}, year = {2025}, eprint = {2508.18265}, archiveprefix = {arXiv} } @article{intphys2018, title = {IntPhys 2019: A Benchmark for Visual Intuitive Physics Understanding}, author = {Ronan Riochet and Mario Ynocente Castro and Mathieu Bernard and Adam Lerer and Rob Fergus and Véronique Izard and Emmanuel Dupoux}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, year = {2022}, volume = {44}, number = {9}, pages = {5016--5025}, doi = {10.1109/tpami.2021.3083839} } @misc{intphys2_2025, title = {IntPhys 2: Benchmarking Intuitive Physics Understanding in Complex Synthetic Environments}, author = {Florian Bordes and Quentin Garrido and Justine T Kao and Adina Williams and Michael Rabbat and Emmanuel Dupoux}, year = {2025}, eprint = {2506.09849}, archiveprefix = {arXiv} } @misc{ipibench2026, title = {IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs Under Continuous Streams}, author = {Jinzhao Li and Yinuo Chen and Wenxuan Song and Yijia Lei and Yichi Zhang and Honglei Yan and Panwang Pan and Miao Liu}, year = {2026}, eprint = {2605.27074}, archiveprefix = {arXiv} } @inproceedings{zhu2025irasim, title = {IRASim: A Fine-Grained World Model for Robot Manipulation}, author = {Zhu, Fangqi and Wu, Hongtao and Guo, Song and Liu, Yuxiao and Cheang, Chilam and Kong, Tao}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {9834--9844}, doi = {10.1109/iccv51701.2025.00917} } @misc{zhu2024soraworldsimulator, title = {Is {Sora} a World Simulator? A Comprehensive Survey on General World Models and Beyond}, author = {Zhu, Zheng and Wang, Xiaofeng and Zhao, Wangbo and Min, Chen and Li, Bohan and Deng, Nianchen and Dou, Min and Wang, Yuqi and Shi, Botian and Wang, Kai and Zhang, Chi and You, Yang and Zhang, Zhaoxiang and Zhao, Dawei and Xiao, Liang and Zhao, Jian and Lu, Jiwen and Huang, Guan}, year = {2024}, eprint = {2405.03520}, archiveprefix = {arXiv} } @inproceedings{bertasius21timesformer, title = {Is Space-Time Attention All You Need for Video Understanding?}, author = {Bertasius, Gedas and Wang, Heng and Torresani, Lorenzo}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, year = {2021}, volume = {139}, pages = {813--824}, } @inproceedings{ivideogpt2024, title = {iVideoGPT: Interactive VideoGPTs Are Scalable World Models}, author = {Wu, Jialong and Yin, Shaofeng and Feng, Ningya and He, Xu and Li, Dong and Hao, Jianye and Long, Mingsheng}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {68082--68119}, doi = {10.52202/079017-2173} } @inproceedings{fang2026iworldbench, title = {i{W}orld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework}, author = {Fang, Jianjie and Lei, Yingshan and Wan, Qin and Wang, Ziyou and Huang, Yuchao and Xu, Yongyan and Zhao, Baining and Zhang, Weichen and Gao, Chen and Chen, Xinlei and Li, Yong}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {29222--29255}, } @inproceedings{wu2025janus, title = {Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation}, author = {Wu, Chengyue and Chen, Xiaokang and Wu, Zhiyu and Ma, Yiyang and Liu, Xingchao and Pan, Zizheng and Liu, Wen and Xie, Zhenda and Yu, Xingkai and Ruan, Chong and Luo, Ping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {12966--12977}, doi = {10.1109/cvpr52734.2025.01210} } @inproceedings{liu2026javisditpp, title = {{JavisDiT++}: Unified Modeling and Optimization for Joint Audio-Video Generation}, author = {Liu, Kai and Zheng, Yanhao and Wang, Kai and Wu, Shengqiong and Zhang, Rongjunchen and Luo, Jiebo and Hatzinakos, Dimitrios and Liu, Ziwei and Fei, Hao and Chua, Tat-Seng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{javisdit2025, title = {{JavisDiT}: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization}, author = {Liu, Kai and Li, Wei and Chen, Lai and Wu, Shengqiong and Zheng, Yanhao and Ji, Jiayi and Zhou, Fan and Luo, Jiebo and Liu, Ziwei and Fei, Hao and Chua, Tat-Seng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{javisgpt2025, title = {{JavisGPT}: A Unified Multi-Modal {LLM} for Sounding-Video Comprehension and Generation}, author = {Liu, Kai and Li, Jungang and Sun, Yuchong and Wu, Shengqiong and gao, jianzhang and Zhang, Daoan and Zhang, Wei and Jin, Sheng and Yu, Sicheng and Zhan, Geng and Ji, Jiayi and Zhou, Fan and Zheng, Liang and Yan, Shuicheng and Fei, Hao and Chua, Tat-Seng}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {142289--142324}, doi = {10.52202/085713-4762} } @misc{alradi2026keepsake, title = {{Keepsake}: Selective Spatial Memory for Long-Horizon Video Generation}, author = {Al Radi, Abdul Mohaimen and Li, Kunyang and Shang, Yuzhang and Shah, Mubarak and Tian, Yu}, year = {2026}, eprint = {2610.06588}, archiveprefix = {arXiv} } @misc{kling2024, title = {Kling {AI}}, author = {{Kuaishou Technology}}, year = {2024}, howpublished = {Product page} } @inproceedings{wang2024koala36m, title = {Koala-36M: A Large-Scale Video Dataset Improving Consistency Between Fine-Grained Conditions and Video Content}, author = {Wang, Qiuheng and Shi, Yukai and Ou, Jiarong and Chen, Rui and Lin, Ke and Wang, Jiahao and Jiang, Boyuan and Yang, Haotian and Zheng, Mingwu and Tao, Xin and Yang, Fei and Wan, Pengfei and Zhang, Di}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {8428--8437}, doi = {10.1109/cvpr52734.2025.00789} } @misc{yang2025keyevl15, title = {Kwai Keye-VL 1.5 Technical Report}, author = {Yang, Biao and Wen, Bin and Ding, Boyang and Liu, Changyi and Chu, Chenglong and Song, Chengru and Rao, Chongling and Yi, Chuan and Li, Da and Zang, Dunju and Yang, Fan and Zhou, Guorui and Zhang, Guowang and Shen, Han and Peng, Hao and Ding, Haojie and Wang, Hao and Fan, Haonan and Ju, Hengrui and Huang, Jiaming and Cao, Jiangxia and Chen, Jiankang and Hua, Jingyun and Chen, Kaibing and Jiang, Kaiyu and Tang, Kaiyu and Gai, Kun and Wei, Muhao and Wang, Qiang and Wang, Ruitao and Na, Sen and Zhang, Shengnan and Mao, Siyang and Huang, Sui and Zhang, Tianke and Gao, Tingting and Chen, Wei and Yuan, Wei and Wu, Xiangyu and Hu, Xiao and Lu, Xingyu and Zhang, Yi-Fan and Yang, Yiping and Chen, Yulong and Lu, Zeyi and Wu, Zhenhua and Ling, Zhixin and Yang, Zhuoran and Li, Ziming and Xu, Di and Gao, Haixuan and Li, Hang and Wang, Jing and Ren, Lejian and Hu, Qigen and Wang, Qianqian and Wang, Shiyao and Luo, Xinchen and Li, Yan and Hu, Yuhang and Zhang, Zixing}, year = {2025}, eprint = {2509.01563}, archiveprefix = {arXiv} } @inproceedings{huang2025ladiwm, title = {LaDi-WM: A Latent Diffusion-Based World Model for Predictive Manipulation}, author = {Huang, Yuhang and Zhang, Jiazhao and Zou, Shilong and Liu, Xinwang and Hu, Ruizhen and Xu, Kai}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, year = {2025}, volume = {305}, pages = {1726--1743}, } @misc{fu2026lance, title = {Lance: Unified Multimodal Modeling by Multi-Task Synergy}, author = {Fengyi Fu and Mengqi Huang and Shaojin Wu and Yunsheng Jiang and Yufei Huo and Hao Li and Yinghang Song and Fei Ding and Jianzhu Guo and Qian He and Zheren Fu and Zhendong Mao and Yongdong Zhang}, year = {2026}, eprint = {2605.18678}, archiveprefix = {arXiv} } @inproceedings{wu2022referformer, title = {Language As Queries for Referring Video Object Segmentation}, author = {Wu, Jiannan and Jiang, Yi and Sun, Peize and Yuan, Zehuan and Luo, Ping}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {4974--4984}, doi = {10.1109/cvpr52688.2022.00492} } @inproceedings{yu2024magvit, title = {Language Model Beats Diffusion -- Tokenizer Is Key to Visual Generation}, author = {Lijun Yu and José Lezama and Nitesh B. Gundavarapu and Luca Versari and Kihyuk Sohn and David Minnen and Yong Cheng and Vighnesh Birodkar and Agrim Gupta and Xiuye Gu and Alexander G. Hauptmann and Boqing Gong and Ming-Hsuan Yang and Irfan Essa and David A. Ross and Lu Jiang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{lasot2018, title = {LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking}, author = {Fan, Heng and Lin, Liting and Yang, Fan and Chu, Peng and Deng, Ge and Yu, Sijia and Bai, Hexin and Xu, Yong and Liao, Chunyuan and Ling, Haibin}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2019}, pages = {5369--5378}, doi = {10.1109/cvpr.2019.00552} } @inproceedings{nikulin2025laom, title = {Latent Action Learning Requires Supervision in the Presence of Distractors}, author = {Nikulin, Alexander and Zisman, Ilya and Tarasov, Denis and Lyubaykin, Nikita and Polubarov, Andrei and Kiselev, Igor and Kurenkov, Vladislav}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {46427--46447}, } @inproceedings{ye2025lapa, title = {Latent Action Pretraining from Videos}, author = {Seonghyeon Ye and Joel Jang and Byeongguk Jeon and Sejune Joo and Jianwei Yang and Baolin Peng and Ajay Mandlekar and Reuben Tan and Yu-Wei Chao and Bill Yuchen Lin and Lars Liden and Kimin Lee and Jianfeng Gao and Luke Zettlemoyer and Dieter Fox and Minjoon Seo}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{chen2026lawam, title = {LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies}, author = {Jialei Chen and Kai Wang and Kang Chen and Shuaihang Chen and Feng Gao and Wenhao Tang and Zhiyuan Li and Weilin Liu and Zhuyu Yao and Boxun Li and Yuanbo Xu and Chao Yu}, year = {2026}, eprint = {2606.15768}, archiveprefix = {arXiv} } @inproceedings{yang2024unisim, title = {Learning Interactive Real-World Simulators}, author = {Sherry Yang and Yilun Du and Seyed Kamyar Seyed Ghasemipour and Jonathan Tompson and Leslie Kaelbling and Dale Schuurmans and Pieter Abbeel}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{ko2024avdc, title = {Learning to Act from Actionless Videos Through Dense Correspondences}, author = {Po-Chen Ko and Jiayuan Mao and Yilun Du and Shao-Hua Sun and Joshua B. Tenenbaum}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{schmidt2024lapo, title = {Learning to Act Without Actions}, author = {Dominik Schmidt and Minqi Jiang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{radford2021learning, title = {Learning Transferable Visual Models from Natural Language Supervision}, author = {Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, year = {2021}, volume = {139}, pages = {8748--8763}, organization = {PmLR} } @inproceedings{du2023unipi, title = {Learning Universal Policies via Text-Guided Video Generation}, author = {Yilun Du and Mengjiao Yang and Bo Dai and Hanjun Dai and Ofir Nachum and Joshua B. Tenenbaum and Dale Schuurmans and Pieter Abbeel}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {9156--9172}, doi = {10.52202/075280-0403} } @misc{maes2026leworldmodel, title = {LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels}, author = {Lucas Maes and Quentin Le Lidec and Damien Scieur and Yann LeCun and Randall Balestriero}, year = {2026}, eprint = {2603.19312}, archiveprefix = {arXiv}, } @misc{wang2024lift, title = {LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment}, author = {Yibin Wang and Zhiyu Tan and Junyan Wang and Xiaomeng Yang and Cheng Jin and Hao Li}, year = {2024}, eprint = {2412.04814}, archiveprefix = {arXiv} } @inproceedings{lv2026lightforcing, title = {Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention}, author = {Lv, Chengtao and Shi, Yumeng and Huang, Yushi and Gong, Ruihao and Ren, Shen and Wang, Wenya}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {83653--83672}, } @inproceedings{liveworldmodel2026, title = {{LIVE}: Long-Horizon Interactive Video World Modeling}, author = {Huang, Junchao and Ye, Ziyang and Hu, Xinting and He, Tianyu and Zhang, Guiyu and Shi, Shaoshuai and Bian, Jiang and Jiang, Li}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {48132--48148}, } @misc{duan2026liveworld, title = {{LiveWorld}: Simulating Out-of-Sight Dynamics in Generative Video World Models}, author = {Duan, Zicheng and Xia, Jiatong and Zhang, Zeyu and Zhang, Wenbo and Zhou, Gengze and Gou, Chenhui and He, Yefei and Chen, Feng and Zhang, Xinyu and Liu, Lingqiao}, year = {2026}, eprint = {2603.07145}, archiveprefix = {arXiv} } @inproceedings{li2024llamavid, title = {LLaMA-VID: An Image Is Worth 2 Tokens in Large Language Models}, author = {Yanwei Li and Chengyao Wang and Jiaya Jia}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, doi = {10.1007/978-3-031-72952-2_19} } @misc{Touvron2023LLaMAOA, title = {LLaMA: Open and Efficient Foundation Language Models}, author = {Hugo Touvron and Thibaut Lavril and Gautier Izacard and Xavier Martinet and Marie-Anne Lachaux and Timothée Lacroix and Baptiste Rozière and Naman Goyal and Eric Hambro and Faisal Azhar and Aurelien Rodriguez and Armand Joulin and Edouard Grave and Guillaume Lample}, year = {2023}, eprint = {2302.13971}, archiveprefix = {arXiv} } @misc{an2026llavaonevision2, title = {LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence}, author = {Xiang An and Yin Xie and Feilong Tang and Yunyao Yan and Huajie Tan and Didi Zhu and Changrui Chen and Xiuwei Zhao and Bin Qin and Kaicheng Yang and Yifei Shen and Yuanhan Zhang and Kaichen Zhang and Wenkang Zhang and Zheng Cheng and Nansen Zhang and Chunsheng Wu and Chunjiang Ge and Zimin Ran and Dehua Song and Chunyuan Li and Shikun Feng and Ming Hu and Zhangquan Chen and Junbo Niu and Bo Li and Ziyong Feng and Ziwei Liu and Zongyuan Ge and Jiankang Deng}, year = {2026}, eprint = {2605.25979}, archiveprefix = {arXiv} } @article{li2024llava, title = {{LL}a{VA}-OneVision: Easy Visual Task Transfer}, author = {Bo Li and Yuanhan Zhang and Dong Guo and Renrui Zhang and Feng Li and Hao Zhang and Kaichen Zhang and Peiyuan Zhang and Yanwei Li and Ziwei Liu and Chunyuan Li}, journal = {Transactions on Machine Learning Research}, year = {2025}, issn = {2835-8856} } @article{zhang2024llavavideo, title = {{LL}a{VA}-Video: Video Instruction Tuning with Synthetic Data}, author = {Yuanhan Zhang and Jinming Wu and Wei Li and Bo Li and Zejun Ma and Ziwei Liu and Chunyuan Li}, journal = {Transactions on Machine Learning Research}, year = {2025}, issn = {2835-8856} } @inproceedings{lian2024llmgrounded, title = {{LLM}-Grounded Video Diffusion Models}, author = {Long Lian and Baifeng Shi and Adam Yala and Trevor Darrell and Boyi Li}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{anne2017localizing, title = {Localizing Moments in Video with Natural Language}, author = {Hendricks, Lisa Anne and Wang, Oliver and Shechtman, Eli and Sivic, Josef and Darrell, Trevor and Russell, Bryan}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, year = {2017}, pages = {5803--5812}, doi = {10.1109/iccv.2017.618} } @article{longva2024, title = {Long Context Transfer from Language to Vision}, author = {Peiyuan Zhang and Kaichen Zhang and Bo Li and Guangtao Zeng and Jingkang Yang and Yuanhan Zhang and Ziyue Wang and Haoran Tan and Chunyuan Li and Ziwei Liu}, journal = {Transactions on Machine Learning Research}, year = {2025}, issn = {2835-8856} } @misc{ma2026beyond3d, title = {Long Time No See: Benchmarking {VLMs} for Out-of-Sight Spatiotemporal Reasoning in Egocentric Videos}, author = {Fangzhou Ma and Ivo Alexander Ban and Eren Homburg and Gabriele Goletto and R{\'e}mi Pautrat and Mahdi Rad and Chiara Plizzari and Marc Pollefeys}, year = {2026}, eprint = {2609.34630}, archiveprefix = {arXiv} } @inproceedings{po2025long, title = {Long-Context State-Space Video World Models}, author = {Po, Ryan and Nitzan, Yotam and Zhang, Richard and Chen, Berlin and Dao, Tri and Shechtman, Eli and Wetzstein, Gordon and Huang, Xun}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {8733--8744}, doi = {10.1109/iccv51701.2025.00817} } @misc{longavcompass2026, title = {LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV}, author = {Tengfei Liu and Yang Shi and Xuanyu Zhu and Jiafu Tang and Liu Yang and Qixun Wang and Zhuoran Zhang and Yuqi Tang and Fengxiang Wang and Yuhao Dong and Xinlong Chen and Bozhou Li and Bohan Zeng and Yue Ding and Xiaohan Zhang and Jialu Chen and Haotian Wang and Yuanxing Zhang and Pengfei Wan and Leye Wang}, year = {2026}, eprint = {2605.26244}, archiveprefix = {arXiv} } @misc{park2026longtake, title = {{LongTake}: Learning to Sustain Dynamics in Long-Horizon Video Generation}, author = {Byoungwoo Park and Jaemoo Choi and Juho Lee and Yongxin Chen}, year = {2026}, eprint = {2609.38562}, archiveprefix = {arXiv} } @inproceedings{liu2025longvideoagent, title = {{L}ong{V}ideo{A}gent: Multi-Agent Reasoning with Long Videos}, author = {Liu, Runtao and Liu, Ziyi and Tang, Jiaqi and Ma, Yue and Pi, Renjie and Zhang, Jipeng and Chen, Qifeng}, booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2026}, pages = {40404--40416}, doi = {10.18653/v1/2026.acl-long.1876}, } @inproceedings{wu2024longvideobench, title = {LongVideoBench: A Benchmark for Long-Context Interleaved Video-Language Understanding}, author = {Wu, Haoning and Li, Dongxu and Chen, Bei and Li, Junnan}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {28828--28857}, doi = {10.52202/079017-0907} } @misc{yu2026longvidsearch, title = {LongVidSearch: An Agentic Benchmark for Multi-Hop Evidence Retrieval Planning in Long Videos}, author = {Rongyi Yu and Chenyuan Duan and Wentao Zhang}, year = {2026}, eprint = {2603.14468}, archiveprefix = {arXiv} } @inproceedings{longvila2024, title = {LongVILA: Scaling Long-Context Visual Language Models for Long Videos}, author = {Yukang Chen and Fuzhao Xue and Dacheng Li and Qinghao Hu and Ligeng Zhu and Xiuyu Li and Yunhao Fang and Haotian Tang and Shang Yang and Zhijian Liu and Ethan He and Hongxu Yin and Pavlo Molchanov and Jan Kautz and Linxi Fan and Yuke Zhu and Yao Lu and Song Han}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{yang2026longvt, title = {LongVT: Incentivizing ''Thinking with Long Videos'' via Native Tool Calling}, author = {Yang, Zuhao and Wang, Sudong and Zhang, Kaichen and Wu, Keming and Leng, Sicong and Zhang, Yifan and Li, Bo and Qin, Chengwei and Lu, Shijian and Li, Xingxuan and Bing, Lidong}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {33816--33826} } @misc{wang2024loong, title = {Loong: Generating Minute-Level Long Videos with Autoregressive Language Models}, author = {Yuqing Wang and Tianwei Xiong and Daquan Zhou and Zhijie Lin and Yang Zhao and Bingyi Kang and Jiashi Feng and Xihui Liu}, year = {2024}, eprint = {2410.02757}, archiveprefix = {arXiv} } @inproceedings{hu2021lora, title = {{LoRA}: Low-Rank Adaptation of Large Language Models}, author = {Edward J. Hu and Yelong Shen and Phillip Wallis and Zeyuan Allen-Zhu and Yuanzhi Li and Shean Wang and Lu Wang and Weizhu Chen}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @misc{hacohen2026ltx2, title = {{LTX-2}: Efficient Joint Audio-Visual Foundation Model}, author = {Yoav HaCohen and Benny Brazowski and Nisan Chiprut and Yaki Bitterman and Andrew Kvochko and Avishai Berkowitz and Daniel Shalem and Daphna Lifschitz and Dudu Moshe and Eitan Porat and Eitan Richardson and Guy Shiran and Itay Chachy and Jonathan Chetboun and Michael Finkelson and Michael Kupchick and Nir Zabari and Nitzan Guetta and Noa Kotler and Ofir Bibi and Ori Gordon and Poriya Panet and Roi Benita and Shahar Armon and Victor Kulikov and Yaron Inger and Yonatan Shiftan and Zeev Melumian and Zeev Farbman}, year = {2026}, eprint = {2601.03233}, archiveprefix = {arXiv} } @misc{hacohen2024ltxvideo, title = {LTX-Video: Realtime Video Latent Diffusion}, author = {Yoav HaCohen and Nisan Chiprut and Benny Brazowski and Daniel Shalem and Dudu Moshe and Eitan Richardson and Eran Levin and Guy Shiran and Nir Zabari and Ori Gordon and Poriya Panet and Sapir Weissbuch and Victor Kulikov and Yaki Bitterman and Zeev Melumian and Ofir Bibi}, year = {2024}, eprint = {2501.00103}, archiveprefix = {arXiv} } @inproceedings{bar2024lumiere, title = {{Lumiere: A Space-Time Diffusion Model for Video Generation}}, author = {Bar-Tal, Omer and Chefer, Hila and Tov, Omer and Herrmann, Charles and Paiss, Roni and Zada, Shiran and Ephrat, Ariel and Hur, Junhwa and Liu, Guanghui and Raj, Amit and Li, Yuanzhen and Rubinstein, Michael and Michaeli, Tomer and Wang, Oliver and Sun, Deqing and Dekel, Tali and Mosseri, Inbar}, booktitle = {SIGGRAPH Asia 2024 Conference Papers}, year = {2024}, pages = {1--11}, doi = {10.1145/3680528.3687614} } @inproceedings{yuan2025lumos, title = {{Lumos-1}: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective}, author = {Hangjie Yuan and Weihua Chen and Jun Cen and Hu Yu and Jingyun Liang and Shuning Chang and Zhihui Lin and Tao Feng and Pengwei Liu and Jiazheng Xing and Hao Luo and Jiasheng Tang and Fan Wang and Yi Yang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{xing2026lumosnexus, title = {Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models}, author = {Xing, Jiazheng and Yuan, Hangjie and Cai, Lingling and Liu, Xinyu and Wei, Yujie and Du, Fei and Feng, Tao and Ci, Hai and Tang, Jiasheng and Chen, Weihua and Wang, Fan and Liu, Yong}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {38--55}, doi = {10.1007/978-3-032-37324-3_3} } @inproceedings{wang2025lvbench, title = {LVBench: An Extreme Long Video Understanding Benchmark}, author = {Wang, Weihan and He, Zehai and Hong, Wenyi and Cheng, Yean and Zhang, Xiaohan and Qi, Ji and Ding, Ming and Gu, Xiaotao and Huang, Shiyu and Xu, Bin and Dong, Yuxiao and Tang, Jie}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {22958--22967}, doi = {10.1109/iccv51701.2025.02131} } @inproceedings{malmm2024, title = {MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding}, author = {He, Bo and Li, Hengduo and Jang, Young Kyun and Jia, Menglin and Cao, Xuefei and Shah, Ashish and Shrivastava, Abhinav and Lim, Ser-Nam}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {13504--13514}, doi = {10.1109/cvpr52733.2024.01282} } @article{teng2025magi, title={MAGI-1: Autoregressive Video Generation at Scale}, author={Teng, Hansi and Jia, Hongyu and Sun, Lei and Li, Lingzhi and Li, Maolin and Tang, Mingqiu and Han, Shuai and Zhang, Tianning and Zhang, WQ and Luo, Weifeng and others}, journal={arXiv preprint arXiv:2505.13211}, year={2025} } @inproceedings{xu2023magicanimate, title = {MagicAnimate: Temporally Consistent Human Image Animation Using Diffusion Model}, author = {Xu, Zhongcong and Zhang, Jianfeng and Liew, Jun Hao and Yan, Hanshu and Liu, Jia-Wei and Zhang, Chenxu and Feng, Jiashi and Shou, Mike Zheng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {1481--1490}, doi = {10.1109/cvpr52733.2024.00147} } @inproceedings{gao2023magicdrive, title = {MagicDrive: Street View Generation with Diverse 3D Geometry Control}, author = {Gao, Ruiyuan and Chen, Kai and Xie, Enze and Hong, Lanqing and Li, Zhenguo and Yeung, Dit-Yan and Xu, Qiang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{singer2023makeavideo, title = {Make-A-Video: Text-to-Video Generation Without Text-Video Data}, author = {Uriel Singer and Adam Polyak and Thomas Hayes and Xi Yin and Jie An and Songyang Zhang and Qiyuan Hu and Harry Yang and Oron Ashual and Oran Gafni and Devi Parikh and Sonal Gupta and Yaniv Taigman}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @inproceedings{ge2024seedllama, title = {Making LLaMA SEE and Draw with SEED Tokenizer}, author = {Ge, Yuying and Zhao, Sijie and Zeng, Ziyun and Ge, Yixiao and Li, Chen and Wang, Xintao and Shan, Ying}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{gu2023mamba, title = {Mamba: Linear-Time Sequence Modeling with Selective State Spaces}, author = {Albert Gu and Tri Dao}, booktitle = {Conference on Language Modeling}, year = {2024} } @misc{shi2026mamoda25, title = {{Mamoda2.5}: Enhancing Unified Multimodal Model with {DiT-MoE}}, author = {Yangming Shi and Shixiang Zhu and Tao Shen and Zhimiao Yu and Dengsheng Chen and Taicai Chen and Yunfei Yang and Juan Zhou and Chen Cheng and Liang Ma and Xibin Wu and Benxuan Yan and Ge Li and Tuoyu Zhang and Dan Li and Chang Liu and Zhenbang Sun}, year = {2026}, eprint = {2605.02641}, archiveprefix = {arXiv} } @inproceedings{he2022masked, title = {Masked Autoencoders Are Scalable Vision Learners}, author = {He, Kaiming and Chen, Xinlei and Xie, Saining and Li, Yanghao and Dollar, Piotr and Girshick, Ross}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {16000--16009}, doi = {10.1109/cvpr52688.2022.01553} } @inproceedings{wei2022maskfeat, title = {Masked Feature Prediction for Self-Supervised Visual Pre-Training}, author = {Wei, Chen and Fan, Haoqi and Xie, Saining and Wu, Chao-Yuan and Yuille, Alan and Feichtenhofer, Christoph}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {14668--14678}, doi = {10.1109/cvpr52688.2022.01426} } @inproceedings{chang2022maskgit, title = {MaskGIT: Masked Generative Image Transformer}, author = {Chang, Huiwen and Zhang, Han and Jiang, Lu and Liu, Ce and Freeman, William T.}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {11315--11325}, doi = {10.1109/cvpr52688.2022.01103} } @article{hafner2023dreamerv3, title = {Mastering Diverse Control Tasks Through World Models}, author = {Hafner, Danijar and Pasukonis, Jurgis and Ba, Jimmy and Lillicrap, Timothy}, journal = {Nature}, year = {2025}, volume = {640}, number = {8059}, pages = {647--653}, doi = {10.1038/s41586-025-08744-2} } @misc{he2025matrixgame2, title = {Matrix-Game 2.0: An Open-Source Real-Time and Streaming Interactive World Model}, author = {Xianglong He and Chunli Peng and Zexiang Liu and Boyang Wang and Yifan Zhang and Qi Cui and Fei Kang and Biao Jiang and Mengyin An and Yangyang Ren and Baixin Xu and Hao-Xiang Guo and Kaixiong Gong and Size Wu and Wei Li and Xuchen Song and Yang Liu and Yangguang Li and Yahui Zhou}, year = {2025}, eprint = {2508.13009}, archiveprefix = {arXiv} } @misc{qian2026matrixgame35, title = {Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory}, author = {Runjia Qian and Zile Wang and Jihai Zhang and Kai Zou and Wei Yu and Jiaxing Li and Zexiang Liu and Yaokun Li and Fei Kang and Kaichen Huang and Mengyin An and Haobo Zhang and Biao Jiang and Jiahua Wang and Haofeng Sun and Yang Liu and Yangguang Li}, year = {2026}, eprint = {2608.29910}, archiveprefix = {arXiv} } @misc{zhang2025matrixgame, title = {Matrix-Game: Interactive World Foundation Model}, author = {Yifan Zhang and Chunli Peng and Boyang Wang and Puyi Wang and Qingcheng Zhu and Fei Kang and Biao Jiang and Zedong Gao and Eric Li and Yang Liu and Yahui Zhou}, year = {2025}, eprint = {2506.18701}, archiveprefix = {arXiv} } @misc{zhang2026mbench, title = {MBench: A Comprehensive Benchmark on Memory Capability for Video World Models}, author = {Shengjun Zhang and Zhang Zhang and Simin Huang and Zhenyu Tang and Hanyang Wang and Chensheng Dai and Min Chen and Yifan Li and Yuxin Li and Yingjie Chen and Hao Liu and Chen Li and Jing Lyu and Yueqi Duan}, year = {2026}, eprint = {2606.00793}, archiveprefix = {arXiv} } @inproceedings{memobench2026, title = {MemoBench: Benchmarking World Modeling in Dynamically Changing Environments}, author = {Chen, Haoyu and Zhou, Kaichen and Hua, Hang and Zhang, Kaile and Qian, Jingwen and Ma, Wufei and Chen, Haonan and Liu, Chunjiang and Zhao, Yizhou and Wang, Xiaoyuan and Li, Weiyue and Yuille, Alan and Liang, Paul Pu and Du, Yilun}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {658--676}, doi = {10.1007/978-3-032-37174-4_38} } @inproceedings{zellers2021merlot, title = {MERLOT: Multimodal Neural Script Knowledge Models}, author = {Zellers, Rowan and Lu, Ximing and Hessel, Jack and Yu, Youngjae and Park, Jae Sung and Cao, Jize and Farhadi, Ali and Choi, Yejin}, booktitle = {Advances in Neural Information Processing Systems}, year = {2021}, volume = {34} } @inproceedings{mevis2023, title = {MeViS: A Large-Scale Benchmark for Video Segmentation with Motion Expressions}, author = {Ding, Henghui and Liu, Chang and He, Shuting and Jiang, Xudong and Loy, Chen Change}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {2694--2703}, doi = {10.1109/iccv51070.2023.00254} } @misc{ye2026mind, title = {MIND: Benchmarking Memory Consistency and Action Control in World Models}, author = {Yixuan Ye and Xuanyu Lu and Yuxin Jiang and Yuchao Gu and Rui Zhao and Qiwei Liang and Jiachun Pan and Fengda Zhang and Weijia Wu and Alex Jinpeng Wang}, year = {2026}, eprint = {2602.08025}, archiveprefix = {arXiv} } @misc{yao2024minicpm, title = {MiniCPM-V: A GPT-4V Level MLLM on Your Phone}, author = {Yuan Yao and Tianyu Yu and Ao Zhang and Chongyi Wang and Junbo Cui and Hongji Zhu and Tianchi Cai and Haoyu Li and Weilin Zhao and Zhihui He and Qianyu Chen and Huarong Zhou and Zhensheng Zou and Haoye Zhang and Shengding Hu and Zhi Zheng and Jie Zhou and Jie Cai and Xu Han and Guoyang Zeng and Dahai Li and Zhiyuan Liu and Maosong Sun}, year = {2024}, eprint = {2408.01800}, archiveprefix = {arXiv} } @misc{zhao2026minwm, title = {minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models}, author = {Zhao, Min and Zhu, Hongzhou and Yan, Bokai and Zhou, Zihan and Chen, Yimin and Wang, Honglie and Sun, Wenqiang and Fang, Zhengwei and Xun, Zizheng and Li, Zihao and Zheng, Kaiwen and He, Guande and Yang, Xiao and Li, Chongxuan and Bao, Fan and Zhu, Jun}, year = {2026}, eprint = {2605.30263}, archiveprefix = {arXiv} } @misc{yang2026mirabench, title = {MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models}, author = {Tianzhuo Yang and Zihan Shen and Zirui Mi and Zhaoyi Zhang and Jiayi Zhou and Jiaming Ji and Juntao Dai and Jiawei Chen and Boyuan Chen and Yaodong Yang}, year = {2026}, eprint = {2605.29360}, archiveprefix = {arXiv} } @inproceedings{tong2025mjvideo, title = {{MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference}}, author = {Tong, Haibo and Wang, Zhaoyang and Chen, Zhaorun and Ji, Haonian and Qiu, Shi and Han, Siwei and Geng, Kexin and Xue, Zhongkai and Zhou, Yiyang and Xia, Peng and Ding, Mingyu and Rafailov, Rafael and Finn, Chelsea and Yao, Huaxiu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {79142--79173}, doi = {10.52202/085713-2647} } @inproceedings{zhou2025mlvu, title = {MLVU: Benchmarking Multi-Task Long Video Understanding}, author = {Zhou, Junjie and Shu, Yan and Zhao, Bo and Wu, Boya and Liang, Zhengyang and Xiao, Shitao and Qin, Minghao and Yang, Xi and Xiong, Yongping and Zhang, Bo and Huang, Tiejun and Liu, Zheng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {13691--13701}, doi = {10.1109/cvpr52734.2025.01278} } @inproceedings{fang2024mmbench, title = {MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding}, author = {Fang, Xinyu and Mao, Kangrui and Duan, Haodong and Zhao, Xiangyu and Li, Yining and Lin, Dahua and Chen, Kai}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {89098--89124}, doi = {10.52202/079017-2827} } @inproceedings{xie2025mmeunify, title = {MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models}, author = {Xie, Wulin and Zhang, Yi-Fan and Fu, Chaoyou and Shi, Yang and Nie, Bingyan and Chen, Hongkai and Zhang, Zhang and Wang, Liang and Tan, Tieniu}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{mmsivideobench2026, title = {MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence}, author = {Jingli Lin and Runsen Xu and Shaohao Zhu and Sihan Yang and Peizhou Cao and Yunlong Ran and Miao Hu and Chenming Zhu and Yiman Xie and Yilin Long and Wenbo Hu and Dahua Lin and Tai Wang and Jiangmiao Pang}, year = {2025}, eprint = {2512.10863}, archiveprefix = {arXiv} } @inproceedings{mmvu2025, title = {MMVU: Measuring Expert-Level Multi-Discipline Video Understanding}, author = {Zhao, Yilun and Zhang, Haowei and Xie, Lujing and Hu, Tongyan and Gan, Guo and Long, Yitao and Hu, Zhiyuan and Chen, Weiyuan and Li, Chuhan and Xu, Zhijian and Wang, Chengye and Shangguan, Ziyao and Liang, Zhenwen and Liu, Yixin and Zhao, Chen and Cohan, Arman}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {8475--8489}, doi = {10.1109/cvpr52734.2025.00793} } @misc{genmo2024mochi, title = {Mochi 1}, author = {{Genmo Team}}, year = {2024}, howpublished = {Official GitHub repository} } @inproceedings{qian2024momentor, title = {{Momentor}: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning}, author = {Qian, Long and Li, Juncheng and Wu, Yu and Ye, Yaobo and Fei, Hao and Chua, Tat-Seng and Zhuang, Yueting and Tang, Siliang}, booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)}, year = {2024}, volume = {235}, pages = {41340--41356}, } @misc{yuan2024mora, title = {Mora: Enabling Generalist Video Generation via a Multi-Agent Framework}, author = {Zhengqing Yuan and Yixin Liu and Yihan Cao and Weixiang Sun and Haolong Jia and Ruoxi Chen and Zhaoxu Li and Bin Lin and Li Yuan and Lifang He and Chi Wang and Yanfang Ye and Lichao Sun}, year = {2024}, eprint = {2403.13248}, archiveprefix = {arXiv} } @misc{gao2026moroute, title = {{MoRoute}: Dynamic Routing for In-Context Multimodal Video Generation}, author = {Chong Gao and Jie Ma and Zhan Peng and Chongxiao Wang and Haoxue Wu and Jun Liang and Guanbin Li and Jing Li}, year = {2026}, eprint = {2607.29545}, archiveprefix = {arXiv} } @misc{motchallenge2016, title = {MOT16: A Benchmark for Multi-Object Tracking}, author = {Anton Milan and Laura Leal-Taixe and Ian Reid and Stefan Roth and Konrad Schindler}, year = {2016}, eprint = {1603.00831}, archiveprefix = {arXiv} } @inproceedings{wang2024motionctrl, title={MotionCtrl: A Unified and Flexible Motion Controller for Video Generation}, author={Wang, Zhouxia and Yuan, Ziyang and Wang, Xintao and Li, Yaowei and Chen, Tianshui and Xia, Menghan and Luo, Ping and Shan, Ying}, booktitle={ACM SIGGRAPH 2024 Conference Papers}, pages={1--11}, year={2024} } @inproceedings{chen2024moto, title = {{Moto}: Latent Motion Token As the Bridging Language for Learning Robot Manipulation from Videos}, author = {Chen, Yi and Ge, Yuying and Tang, Weiliang and Li, Yizhuo and Ge, Yixiao and Ding, Mingyu and Shan, Ying and Liu, Xihui}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {19752--19763}, doi = {10.1109/iccv51701.2025.01837} } @misc{polyak2024moviegen, title = {Movie Gen: A Cast of Media Foundation Models}, author = {Adam Polyak and Amit Zohar and Andrew Brown and Andros Tjandra and Animesh Sinha and Ann Lee and Apoorv Vyas and Bowen Shi and Chih-Yao Ma and Ching-Yao Chuang and David Yan and Dhruv Choudhary and Dingkang Wang and Geet Sethi and Guan Pang and Haoyu Ma and Ishan Misra and Ji Hou and Jialiang Wang and Kiran Jagadeesh and Kunpeng Li and Luxin Zhang and Mannat Singh and Mary Williamson and Matt Le and Matthew Yu and Mitesh Kumar Singh and Peizhao Zhang and Peter Vajda and Quentin Duval and Rohit Girdhar and Roshan Sumbaly and Sai Saketh Rambhatla and Sam Tsai and Samaneh Azadi and Samyak Datta and Sanyuan Chen and Sean Bell and Sharadh Ramaswamy and Shelly Sheynin and Siddharth Bhattacharya and Simran Motwani and Tao Xu and Tianhe Li and Tingbo Hou and Wei-Ning Hsu and Xi Yin and Xiaoliang Dai and Yaniv Taigman and Yaqiao Luo and Yen-Cheng Liu and Yi-Chiao Wu and Yue Zhao and Yuval Kirstain and Zecheng He and Zijian He and Albert Pumarola and Ali Thabet and Artsiom Sanakoyeu and Arun Mallya and Baishan Guo and Boris Araya and Breena Kerr and Carleigh Wood and Ce Liu and Cen Peng and Dimitry Vengertsev and Edgar Schonfeld and Elliot Blanchard and Felix Juefei-Xu and Fraylie Nord and Jeff Liang and John Hoffman and Jonas Kohler and Kaolin Fire and Karthik Sivakumar and Lawrence Chen and Licheng Yu and Luya Gao and Markos Georgopoulos and Rashel Moritz and Sara K. Sampson and Shikai Li and Simone Parmeggiani and Steve Fine and Tara Fowler and Vladan Petrovic and Yuming Du}, year = {2024}, eprint = {2410.13720}, archiveprefix = {arXiv} } @inproceedings{song2024moviechat, title = {MovieChat: From Dense Token to Sparse Memory for Long Video Understanding}, author = {Song, Enxin and Chai, Wenhao and Wang, Guanhong and Zhang, Yucheng and Zhou, Haoyang and Wu, Feiyang and Chi, Haozhe and Guo, Xun and Ye, Tian and Zhang, Yanting and Lu, Yan and Hwang, Jenq-Neng and Wang, Gaoang}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {18221--18232}, doi = {10.1109/cvpr52733.2024.01725} } @misc{shang2025mowm, title = {MoWM: Mixture-of-World-Models for Embodied Planning via Latent-to-Pixel Feature Modulation}, author = {Yangcheng Yu and Xin Jin and Yu Shang and Xin Zhang and Haisheng Su and Wei Wu and Yong Li}, year = {2025}, eprint = {2509.21797}, archiveprefix = {arXiv} } @inproceedings{Xu_2016_CVPR, title = {MSR-VTT: A Large Video Description Dataset for Bridging Video and Language}, author = {Xu, Jun and Mei, Tao and Yao, Ting and Rui, Yong}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2016}, pages = {5288--5296}, doi = {10.1109/cvpr.2016.571} } @inproceedings{shi2026msvbench, title = {{MSVB}ench: Towards Human-Level Evaluation of Multi-Shot Video Generation}, author = {Shi, Haoyuan and li, Yunxin and Deng, Nanhao and Xu, Zhenran and Chen, Xinyu and Wang, Longyue and Hu, Baotian and Zhang, Min}, booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026}, year = {2026}, pages = {24034--24058}, doi = {10.18653/v1/2026.findings-acl.1203}, } @misc{multirefcompass2026, title = {MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation}, author = {Xiaohan Zhang and Yuqing Wen and Junlin Chen and Yuqi Tang and Yiting He and Lizhuo Shao and Weiming Zhu and Tengfei Liu and Yang Shi and Jialu Chen and Yuanxing Zhang and Huaxiong Li}, year = {2026}, eprint = {2607.14189}, archiveprefix = {arXiv} } @misc{multiworld2026, title = {MultiWorld: Scalable Multi-Agent Multi-View Video World Models}, author = {Haoyu Wu and Jiwen Yu and Yingtian Zou and Xihui Liu}, year = {2026}, eprint = {2604.18564}, archiveprefix = {arXiv} } @misc{zhang2024musetalk, title = {MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling}, author = {Yue Zhang and Zhizhou Zhong and Minhao Liu and Zhaokang Chen and Bin Wu and Yubin Zeng and Chao Zhan and Yingjie He and Junxin Huang and Wenjiang Zhou}, year = {2024}, eprint = {2410.10122}, archiveprefix = {arXiv} } @misc{zhang2026muss, title = {{MuSS}: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation}, author = {Haojie Zhang and Di Wu and Bingyan Liu and Linjie Zhong and Yuancheng Wei and Xingsong Ye and Nanqing Liu and Yaling Liang}, year = {2026}, eprint = {2604.23789}, archiveprefix = {arXiv} } @inproceedings{li2024mvbench, title = {MVBench: A Comprehensive Multi-Modal Video Understanding Benchmark}, author = {Li, Kunchang and Wang, Yali and He, Yinan and Li, Yizhuo and Wang, Yi and Liu, Yi and Wang, Zun and Xu, Jilan and Chen, Guo and Luo, Ping and Wang, Limin and Qiao, Yu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {22195--22206}, doi = {10.1109/cvpr52733.2024.02095} } @inproceedings{nwm2024, title = {Navigation World Models}, author = {Bar, Amir and Zhou, Gaoyue and Tran, Danny and Darrell, Trevor and LeCun, Yann}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {15791--15801}, doi = {10.1109/cvpr52734.2025.01472} } @inproceedings{van2017neural, title = {Neural Discrete Representation Learning}, author = {van den Oord, Aaron and Vinyals, Oriol and Kavukcuoglu, Koray}, booktitle = {Advances in Neural Information Processing Systems}, year = {2017}, volume = {30}, } @misc{xu2026nextforcing, title = {Next Forcing: Causal World Modeling with Multi-Chunk Prediction}, author = {Gangwei Xu and Qihang Zhang and Jiaming Zhou and Xing Zhu and Yujun Shen and Xin Yang and Yinghao Xu}, year = {2026}, eprint = {2606.11187}, archiveprefix = {arXiv} } @inproceedings{wu2023nextgpt, title = {{NExT-GPT}: Any-to-Any Multimodal {LLM}}, author = {Wu, Shengqiong and Fei, Hao and Qu, Leigang and Ji, Wei and Chua, Tat-Seng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {53366--53397}, } @inproceedings{luo2025nextomni, title = {NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching}, author = {Luo, Run and Xia, Xiaobo and Wang, Lu and Chen, Longze and Shan, Renke and Luo, Jing and Yang, Min and Chua, Tat-Seng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{xiao2021next, title = {NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions}, author = {Xiao, Junbin and Shang, Xindi and Yao, Angela and Chua, Tat-Seng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, pages = {9777--9786}, doi = {10.1109/cvpr46437.2021.00965} } @inproceedings{tian2025nuscenesspatialqa, title = {NuScenes-SpatialQA: A Spatial Understanding and Reasoning Benchmark for Vision-Language Models in Autonomous Driving}, author = {Tian, Kexin and Mao, Jingrui and Zhang, Yunlong and Jiang, Jiwan and Zhou, Yang and Tu, Zhengzhong}, booktitle = {2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)}, year = {2025}, pages = {4626--4635}, doi = {10.1109/iccvw69036.2025.00480} } @inproceedings{caesar2020nuscenes, title = {nuScenes: A Multimodal Dataset for Autonomous Driving}, author = {Caesar, Holger and Bankiti, Varun and Lang, Alex H. and Vora, Sourabh and Liong, Venice Erin and Xu, Qiang and Krishnan, Anush and Pan, Yu and Baldan, Giancarlo and Beijbom, Oscar}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, pages = {11618--11628}, doi = {10.1109/cvpr42600.2020.01164} } @inproceedings{yin2023nuwa, title = {NUWA-XL: Diffusion Over Diffusion for eXtremely Long Video Generation}, author = {Yin, Shengming and Wu, Chenfei and Yang, Huan and Wang, Jianfeng and Wang, Xiaodong and Ni, Minheng and Yang, Zhengyuan and Li, Linjie and Liu, Shuguang and Yang, Fan and Fu, Jianlong and Gong, Ming and Wang, Lijuan and Liu, Zicheng and Li, Houqiang and Duan, Nan}, booktitle = {Proceedings of the 61st Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2023}, pages = {1309--1320}, doi = {10.18653/v1/2023.acl-long.73} } @misc{basant2026omnidreams, title = {{NVIDIA OmniDreams}: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation}, author = {Basant, Aarti and Kar, Amlan and Paschalidou, Despoina and Wei, Fangyin and Ferroni, Francesco and Garcia Cobo, Guillermo and Turki, Haithem and Ling, Huan and Seo, Jaewoo and Lucas, James and Wu, Jay Zhangjie and Wang, Jialiang and Lorraine, Jonathan and Gao, Jun and He, Kai and Tothova, Katarina and Xie, Kevin and Tyszkiewicz, Michal and Wu, Qi and de Lutio, Riccardo and Li, Ruilong and Fidler, Sanja and Kim, Seung Wook and Shen, Tianchang and Cao, Tianshi and Pfaff, Tobias and Lew, William and Wu, Xindi and Ren, Xuanchi and Lu, Yifan and Zhang, Yuxuan and Gojcic, Zan and Wang, Zian}, year = {2026}, eprint = {2606.03159}, archiveprefix = {arXiv} } @misc{oasis2024, title = {Oasis: A Universe in a Transformer}, author = {{Decart} and {Etched} and Quevedo, Julian and McIntyre, Quinn and Campbell, Spruce and Chen, Xinlei and Wachen, Robert}, year = {2024}, howpublished = {Official project page} } @misc{yang2026omnivideo2, title = {Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing}, author = {Hao Yang and Zhiyu Tan and Jia Gong and Luozheng Qin and Hesen Chen and Xiaomeng Yang and Yuqing Sun and Yuetan Lin and Mengping Yang and Hao Li}, year = {2026}, eprint = {2602.08820}, archiveprefix = {arXiv} } @misc{tan2025omnivideo, title = {Omni-Video: Democratizing Unified Video Understanding and Generation}, author = {Zhiyu Tan and Hao Yang and Luozheng Qin and Jia Gong and Mengping Yang and Hao Li}, year = {2025}, eprint = {2507.06119}, archiveprefix = {arXiv} } @inproceedings{wang2025omnidrive, title = {OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning}, author = {Wang, Shihao and Yu, Zhiding and Jiang, Xiaohui and Lan, Shiyi and Shi, Min and Chang, Nadine and Kautz, Jan and Li, Ying and Alvarez, Jose M.}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {22442--22452}, doi = {10.1109/cvpr52734.2025.02090} } @misc{lu2026omniinteract, title = {OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants}, author = {Xudong Lu and Xueying Li and Annan Wang and Yang Bo and Jinpeng Chen and Zengliang Li and Nianzu Yang and Rui Liu and Xue Yang and Jingwen Hou and Hongsheng Li}, year = {2026}, eprint = {2605.26485}, archiveprefix = {arXiv} } @misc{li2026omnivbench, title = {{OmniVBench}: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation}, author = {Wenxue Li and Peiyan Guan and Haoyang Jiang and Junxian Cai and Hualuo Liu and Chunjie Zhang and Chong Guan and Kai Huang and Songlian Li and Taiyi Wu and Yongjian Yu and Xiaotong Zhao and Alan Zhao and Quande Liu and Xi Chen and Yu Liu and Lei Zhu}, year = {2026}, eprint = {2609.22069}, archiveprefix = {arXiv} } @inproceedings{li2025omnivideobench, title = {OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs}, author = {Li, Caorui and Chen, Yu and Ji, Yiyan and Xu, Jin and Cui, Zhenyu and Li, Shihao and Zhang, Yuanxing and Wang, Wentao and Song, Zhenghao and Zhang, Dingling and He, Ying and Liu, Haoxiang and Wang, Yuxuan and Wang, Qiufeng and Tang, Jiafu and Wu, Zhenhe and Luo, Jiehui and Pan, Zhiyu and Xie, Weihao and Zhang, Chenchen and Wang, Zhaohui and Tian, Jiayi and Wang, Yanghai and Cao, Zhe and Dai, Minxin and Wang, Ke and Wen, Runzhe and Ma, Yinghao and Pan, Yaning and Chang, Sungkyun and Taheri, Termeh and Xia, Haiwen and Plachouras, Christos and Benetos, Emmanouil and Li, Yizhi and Zhang, Ge and Yang, Jian and Peng, Tianhao and Wang, Zili and Liu, Minghao and Peng, Junran and Zhang, Zhaoxiang and Liu, Jiaheng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{pan2026omniweaving, title = {OmniWeaving: Towards Unified Video Generation with Free-Form Composition and Reasoning}, author = {Pan, Kaihang and Tian, Qi and Zhang, Jianwei and Kong, Weijie and Xiong, Jiangfeng and Long, Yanxin and Zhang, Shixue and Qiu, Haiyi and Wang, Tan and Lv, Zheqi and Tu, Shuyuan and Wu, Yue and Bo, Liefeng and Tang, Siliang and Zhong, Zhao}, year = {2026}, eprint = {2603.24458}, archiveprefix = {arXiv} } @inproceedings{omniworlddata2025, title = {OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling}, author = {Zhou, Yang and Wang, Yifan and Zhou, Jianjun and Chang, Wenzheng and Guo, Haoyu and Li, Zizun and Ma, Kaijing and Li, Xinyue and Wang, Yating and Zhu, Haoyi and Liu, Mingyu and Liu, Dingning and Yang, Jiange and Fu, Zhoujie and Chen, Junyi and Shen, Chunhua and Pang, Jiangmiao and Zhang, Kaipeng and He, Tong}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{ge2024fvdbias, title = {On the Content Bias in Frechet Video Distance}, author = {Ge, Songwei and Mahapatra, Aniruddha and Parmar, Gaurav and Zhu, Jun-Yan and Huang, Jia-Bin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {7277--7288}, doi = {10.1109/cvpr52733.2024.00695} } @misc{feng2026oneforcing, title = {One-Forcing: Towards Stable One-Step Autoregressive Video Generation}, author = {Jiaqi Feng and Justin Cui and Yuanhao Ban and Cho-Jui Hsieh}, year = {2026}, eprint = {2605.23458}, archiveprefix = {arXiv} } @inproceedings{dalal2025tttvideo, title = {One-Minute Video Generation with Test-Time Training}, author = {Dalal, Karan and Koceja, Daniel and Xu, Jiarui and Zhao, Yue and Han, Shihao and Cheung, Ka Chun and Kautz, Jan and Choi, Yejin and Sun, Yu and Wang, Xiaolong}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {17702--17711}, doi = {10.1109/cvpr52734.2025.01649} } @misc{zeng2026onestreamer, title = {{OneStreamer}: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction}, author = {Xiangyu Zeng and Yuandong Yang and Zhiqiu Zhang and Yuhan Zhu and Xinhao Li and Qingyi Si and Dingyu Yao and Changlian Ma and Haoran Chen and Xinyu Chen and Yansong Shi and Junhao Zhou and Yifei Li and Jun Zhang and Chuanyu Qin and Chenxu Yang and Xinlei Yu and Kun Ouyang and Yuchen Shao and Qianshan Wei and Changhai Zhou and Jun Gao and Jiaqi Wang and Limin Wang}, year = {2026}, eprint = {2610.01762}, archiveprefix = {arXiv} } @inproceedings{feng2025onethinker, title = {OneThinker: All-in-One Reasoning Model for Image and Video}, author = {Feng, Kaituo and Zhang, Manyuan and Li, Hongyu and Fan, Kaixuan and Chen, Shuang and Jiang, Yilei and Zheng, Dian and Sun, Peiwen and Zhang, Yiyuan and Sun, Haoze and Feng, Yan and Pei, Peng and Cai, Xunliang and Yue, Xiangyu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {5432--5443}, } @inproceedings{zhou2025onevae, title = {OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better}, author = {Zhou, Yupeng and Li, Zhen and Chen, Yuming and Ouyang, Ziheng and Du, Ruoyi and Zhou, Daquan and Fu, Bin and Liu, Yihao and Gao, Peng and Cheng, Ming-Ming and Hou, Qibin}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {533--553}, doi = {10.1007/978-3-032-37152-2_29} } @misc{he2026oneworld, title = {OneWorld: Learning Consistent Physics Across Actions in World Models}, author = {Ke He and Yichen Ding and Bin Yang}, year = {2026}, eprint = {2609.30946}, archiveprefix = {arXiv} } @inproceedings{openx2023embodiment, title = {Open X-Embodiment: Robotic Learning Datasets and RT-X Models}, author = {O’Neill, Abby and Rehman, Abdul and Maddukuri, Abhiram and Gupta, Abhishek and Padalkar, Abhishek and Lee, Abraham and Pooley, Acorn and Gupta, Agrim and Mandlekar, Ajay and Jain, Ajinkya and Tung, Albert and Bewley, Alex and Herzog, Alex and Irpan, Alex and Khazatsky, Alexander and Rai, Anant and Gupta, Anchit and Wang, Andrew and Singh, Anikait and Garg, Animesh and Kembhavi, Aniruddha and Xie, Annie and Brohan, Anthony and Raffin, Antonin and Sharma, Archit and Yavary, Arefeh and Jain, Arhan and Balakrishna, Ashwin and Wahid, Ayzaan and Burgess-Limerick, Ben and Kim, Beomjoon and Schölkopf, Bernhard and Wulfe, Blake and Ichter, Brian and Lu, Cewu and Xu, Charles and Le, Charlotte and Finn, Chelsea and Wang, Chen and Xu, Chenfeng and Chi, Cheng and Huang, Chenguang and Chan, Christine and Agia, Christopher and Pan, Chuer and Fu, Chuyuan and Devin, Coline and Xu, Danfei and Morton, Daniel and Driess, Danny and Chen, Daphne and Pathak, Deepak and Shah, Dhruv and Büchler, Dieter and Jayaraman, Dinesh and Kalashnikov, Dmitry and Sadigh, Dorsa and Johns, Edward and Foster, Ethan and Liu, Fangchen and Ceola, Federico and Xia, Fei and Zhao, Feiyu and Stulp, Freek and Zhou, Gaoyue and Sukhatme, Gaurav S. and Salhotra, Gautam and Yan, Ge and Feng, Gilbert and Schiavi, Giulio and Berseth, Glen and Kahn, Gregory and Wang, Guanzhi and Su, Hao and Fang, Hao-Shu and Shi, Haochen and Bao, Henghui and Ben Amor, Heni and Christensen, Henrik I and Furuta, Hiroki and Walke, Homer and Fang, Hongjie and Ha, Huy and Mordatch, Igor and Radosavovic, Ilija and Leal, Isabel and Liang, Jacky and Abou-Chakra, Jad and Kim, Jaehyung and Drake, Jaimyn and Peters, Jan and Schneider, Jan and Hsu, Jasmine and Bohg, Jeannette and Bingham, Jeffrey and Wu, Jeffrey and Gao, Jensen and Hu, Jiaheng and Wu, Jiajun and Wu, Jialin and Sun, Jiankai and Luo, Jianlan and Gu, Jiayuan and Tan, Jie and Oh, Jihoon and Wu, Jimmy and Lu, Jingpei and Yang, Jingyun and Malik, Jitendra and Silvério, João and Hejna, Joey and Booher, Jonathan and Tompson, Jonathan and Yang, Jonathan and Salvador, Jordi and Lim, Joseph J. and Han, Junhyek and Wang, Kaiyuan and Rao, Kanishka and Pertsch, Karl and Hausman, Karol and Go, Keegan and Gopalakrishnan, Keerthana and Goldberg, Ken and Byrne, Kendra and Oslund, Kenneth and Kawaharazuka, Kento and Black, Kevin and Lin, Kevin and Zhang, Kevin and Ehsani, Kiana and Lekkala, Kiran and Ellis, Kirsty and Rana, Krishan and Srinivasan, Krishnan and Fang, Kuan and Singh, Kunal Pratap and Zeng, Kuo-Hao and Hatch, Kyle and Hsu, Kyle and Itti, Laurent and Chen, Lawrence Yunliang and Pinto, Lerrel and Fei-Fei, Li and Tan, Liam and Fan, Linxi Jim and Ott, Lionel and Lee, Lisa and Weihs, Luca and Chen, Magnum and Lepert, Marion and Memmel, Marius and Tomizuka, Masayoshi and Itkina, Masha and Castro, Mateo Guaman and Spero, Max and Du, Maximilian and Ahn, Michael and Yip, Michael C. and Zhang, Mingtong and Ding, Mingyu and Heo, Minho and Srirama, Mohan Kumar and Sharma, Mohit and Kim, Moo Jin and Kanazawa, Naoaki and Hansen, Nicklas and Heess, Nicolas and Joshi, Nikhil J and Suenderhauf, Niko and Liu, Ning and Di Palo, Norman and Shafiullah, Nur Muhammad Mahi and Mees, Oier and Kroemer, Oliver and Bastani, Osbert and Sanketi, Pannag R and Miller, Patrick Tree and Yin, Patrick and Wohlhart, Paul and Xu, Peng and Fagan, Peter David and Mitrano, Peter and Sermanet, Pierre and Abbeel, Pieter and Sundaresan, Priya and Chen, Qiuyu and Vuong, Quan and Rafailov, Rafael and Tian, Ran and Doshi, Ria and Martín-Martín, Roberto and Baijal, Rohan and Scalise, Rosario and Hendrix, Rose and Lin, Roy and Qian, Runjia and Zhang, Ruohan and Mendonca, Russell and Shah, Rutav and Hoque, Ryan and Julian, Ryan and Bustamante, Samuel and Kirmani, Sean and Levine, Sergey and Lin, Shan and Moore, Sherry and Bahl, Shikhar and Dass, Shivin and Sonawani, Shubham and Song, Shuran and Xu, Sichun and Haldar, Siddhant and Karamcheti, Siddharth and Adebola, Simeon and Guist, Simon and Nasiriany, Soroush and Schaal, Stefan and Welker, Stefan and Tian, Stephen and Ramamoorthy, Subramanian and Dasari, Sudeep and Belkhale, Suneel and Park, Sungjae and Nair, Suraj and Mirchandani, Suvir and Osa, Takayuki and Gupta, Tanmay and Harada, Tatsuya and Matsushima, Tatsuya and Xiao, Ted and Kollar, Thomas and Yu, Tianhe and Ding, Tianli and Davchev, Todor and Zhao, Tony Z. and Armstrong, Travis and Darrell, Trevor and Chung, Trinity and Jain, Vidhi and Vanhoucke, Vincent and Zhan, Wei and Zhou, Wenxuan and Burgard, Wolfram and Chen, Xi and Wang, Xiaolong and Zhu, Xinghao and Geng, Xinyang and Liu, Xiyuan and Liangwei, Xu and Li, Xuanlin and Lu, Yao and Ma, Yecheng Jason and Kim, Yejin and Chebotar, Yevgen and Zhou, Yifan and Zhu, Yifeng and Wu, Yilin and Xu, Ying and Wang, Yixuan and Bisk, Yonatan and Cho, Yoonyoung and Lee, Youngwoon and Cui, Yuchen and Cao, Yue and Wu, Yueh-Hua and Tang, Yujin and Zhu, Yuke and Zhang, Yunchu and Jiang, Yunfan and Li, Yunshuang and Li, Yunzhu and Iwasawa, Yusuke and Matsuo, Yutaka and Ma, Zehan and Xu, Zhuo and Cui, Zichen Jeff and Zhang, Zichen and Lin, Zipeng}, booktitle = {2024 IEEE International Conference on Robotics and Automation (ICRA)}, year = {2024}, pages = {6892--6903}, doi = {10.1109/icra57147.2024.10611477} } @misc{zheng2024opensora, title = {Open-Sora: Democratizing Efficient Video Production for All}, author = {Zheng, Zangwei and Peng, Xiangyu and Yang, Tianji and Shen, Chenhui and Li, Shenggui and Liu, Hongxin and Zhou, Yukun and Li, Tianyi and You, Yang}, year = {2024}, eprint = {2412.20404}, archiveprefix = {arXiv} } @misc{opencof2026, title = {OpenCoF: Learning to Reason Through Video Generation}, author = {Xinyan Chen and Ziyu Guo and Renrui Zhang and Dongzhi Jiang and Hongsheng Li}, year = {2026}, eprint = {2607.08763}, archiveprefix = {arXiv} } @inproceedings{li2025openhumanvid, title = {OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation}, author = {Li, Hui and Xu, Mingwang and Zhan, Yun and Mu, Shan and Li, Jiaye and Cheng, Kaihui and Chen, Yuxuan and Chen, Tan and Ye, Mao and Wang, Jingdong and Zhu, Siyu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {7752--7762}, doi = {10.1109/cvpr52734.2025.00726} } @inproceedings{he2025openve, title = {{OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing Supplementary Material}}, author = {He, Haoyang and Wang, Jie and Zhang, Jiangning and Xue, Zhucun and Bu, Xingyuan and Yang, Qiangpeng and Wen, Shilei and Xie, Lei}, booktitle = {Computer Vision -- ECCV 2026}, year = {2026}, volume = {17029}, pages = {607--623}, doi = {10.1007/978-3-032-37627-5_33}, } @inproceedings{nan2025openvid, title = {OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-Video Generation}, author = {Nan, Kepan and Xie, Rui and Zhou, Penghao and Fan, Tiehan and Yang, Zhenheng and Chen, Zhijie and Li, Xiang and Yang, Jian and Tai, Ying}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{ma2026stevobench, title = {Out of Sight, Out of Mind? Evaluating State Evolution in Video World Models}, author = {Ma, Ziqi and Liufu, Mengzhan and Gkioxari, Georgia}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {129--146}, doi = {10.1007/978-3-032-37258-1_8} } @misc{ovi2025, title = {Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation}, author = {Chetwin Low and Weimin Wang and Calder Katyal}, year = {2025}, eprint = {2510.01284}, archiveprefix = {arXiv} } @inproceedings{niu2025ovo, title = {OVO-Bench: How Far Is Your Video-LLMs from Real-World Online Video Understanding?}, author = {Niu, Junbo and Li, Yifei and Miao, Ziyang and Ge, Chunjiang and Zhou, Yuanhang and He, Qihao and Dong, Xiaoyi and Duan, Haodong and Ding, Shuangrui and Qian, Rui and Zhang, Pan and Zang, Yuhang and Cao, Yuhang and He, Conghui and Wang, Jiaqi}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {18902--18913}, doi = {10.1109/cvpr52734.2025.01761} } @misc{li2026ovosbench, title = {{OVO-S-Bench}: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal {LLMs}}, author = {Yifei Li and Pengyiang Liu and Yuhang Zang and Zhongyue Shi and Qi Fu and Hongye Hao and Jiwen Lu}, year = {2026}, eprint = {2606.03890}, archiveprefix = {arXiv} } @misc{huang2024owl1, title = {Owl-1: Omni World Model for Consistent Long Video Generation}, author = {Yuanhui Huang and Wenzhao Zheng and Yuan Gao and Xin Tao and Pengfei Wan and Di Zhang and Jie Zhou and Jiwen Lu}, year = {2024}, eprint = {2412.09600}, archiveprefix = {arXiv} } @inproceedings{zhou2025paibench, title = {PAI-Bench: A Comprehensive Benchmark for Physical AI}, author = {Zhou, Fengzhe and Huang, Jiannan and Li, Jialuo and Ramanan, Deva and Shi, Humphrey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {21522--21536}, } @inproceedings{wen2023panacea, title = {{Panacea}: Panoramic and Controllable Video Generation for Autonomous Driving}, author = {Wen, Yuqing and Zhao, Yucheng and Liu, Yingfei and Jia, Fan and Wang, Yanhui and Luo, Chong and Zhang, Chi and Wang, Tiancai and Sun, Xiaoyan and Zhang, Xiangyu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {6902--6912}, doi = {10.1109/cvpr52733.2024.00659} } @inproceedings{chen2024panda, title = {Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers}, author = {Chen, Tsai-Shien and Siarohin, Aliaksandr and Menapace, Willi and Deyneka, Ekaterina and Chao, Hsiang-wei and Jeon, Byung Eun and Fang, Yuwei and Lee, Hsin-Ying and Ren, Jian and Yang, Ming-Hsuan and Tulyakov, Sergey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {13320--13331}, doi = {10.1109/cvpr52733.2024.01265} } @misc{pandora2024, title = {Pandora: Towards General World Model with Natural Language Actions and Video States}, author = {Jiannan Xiang and Guangyi Liu and Yi Gu and Qiyue Gao and Yuting Ning and Yuheng Zha and Zeyu Feng and Tianhua Tao and Shibo Hao and Yemin Shi and Zhengzhong Liu and Eric P. Xing and Zhiting Hu}, year = {2024}, eprint = {2406.09455}, archiveprefix = {arXiv} } @inproceedings{luo2024panosent, title = {{PanoSent}: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-Based Sentiment Analysis}, author = {Luo, Meng and Fei, Hao and Li, Bobo and Wu, Shengqiong and Liu, Qian and Poria, Soujanya and Cambria, Erik and Lee, Mong-Li and Hsu, Wynne}, booktitle = {Proceedings of the 32nd ACM International Conference on Multimedia}, year = {2024}, pages = {7667--7676}, doi = {10.1145/3664647.3680705} } @misc{pu2026pawbench, title = {PAWBench: How Far Are We from Probabilistically Aligned World Modeling?}, author = {Yuandong Pu and Le Zhuo and Sayak Paul and Gabriel Jorge Menezes and Avram Đorđević and Shiyang Li and Yifan Zhou and Bin Fu and Wenlong Zhang and Junjun He and Yu Qiao and Yihao Liu and Jinbo Xing and Xi Chen}, year = {2026}, eprint = {2608.27345}, archiveprefix = {arXiv} } @inproceedings{jaegle2021perceiver, title = {Perceiver: General Perception with Iterative Attention}, author = {Andrew Jaegle and Felix Gimeno and Andrew Brock and Andrew Zisserman and Oriol Vinyals and Joao Carreira}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, year = {2021}, volume = {139}, pages = {4651--4664}, } @inproceedings{bolya2025pe, title = {Perception Encoder: The Best Visual Embeddings Are Not at the Output of the Network}, author = {Bolya, Daniel and Huang, Po-Yao and Sun, Peize and Cho, Jang Hyun and Madotto, Andrea and Wei, Chen and Ma, Tengyu and Zhi, Jiale and Rajasegaran, Jathushan and Rasheed, Hanoona and Wang, Junke and Monteiro, Marco and Xu, Hu and Dong, Shiyu and Ravi, Nikhila and Li, Daniel and Dollar, Piotr and Feichtenhofer, Christoph}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {60884--60937}, doi = {10.52202/085713-2036} } @inproceedings{chen2025phantomdata, title = {Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset}, author = {Chen, Zhuowei and Li, Bingchuan and Ma, Tianxiang and Liu, Lijie and Liu, Mingcong and Jiang, Yunsheng and Li, Gen and Li, Xinghui and Chen, Liyang and Zhou, Siyu and He, Qian and Wu, Xinglong}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{shen2026phantom, title = {PHANTOM: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics}, author = {Shen, Ying and Xiong, Jerry and Yu, Tianjiao and Lourentzou, Ismini}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {11185--11194} } @inproceedings{villegas2023phenaki, title = {Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions}, author = {Ruben Villegas and Mohammad Babaeizadeh and Pieter-Jan Kindermans and Hernan Moraldo and Han Zhang and Mohammad Taghi Saffar and Santiago Castro and Julius Kunze and Dumitru Erhan}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @misc{phyavbench2025, title = {PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation}, author = {Tianxin Xie and Wentao Lei and Kai Jiang and Guanjie Huang and Pengfei Zhang and Chunhui Zhang and Fengji Ma and Haoyu He and Han Zhang and Jiangshan He and Jinting Wang and Linghan Fang and Lufei Gao and Orkesh Ablet and Peihua Zhang and Ruolin Hu and Shengyu Li and Weilin Lin and Xiaoyang Feng and Xinyue Yang and Yan Rong and Yanyun Wang and Zihang Shao and Zelin Zhao and Chenxing Li and Shan Yang and Wenfu Wang and Meng Yu and Dong Yu and Li Liu}, year = {2025}, eprint = {2512.23994}, archiveprefix = {arXiv} } @inproceedings{cai2025phygdpo, title = {PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation}, author = {Cai, Yuanhao and Li, Kunpeng and Jia, Menglin and Wang, Jialiang and Sun, Junzhe and Liang, Feng and Chen, Weifeng and Juefei-Xu, Felix and Wang, Chu and Thabet, Ali and Dai, Xiaoliang and Ju, Xuan and Yuille, Alan and Hou, Ji}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {91--109}, doi = {10.1007/978-3-032-37624-4_6} } @misc{ku2026phyprobe, title = {{PhyProbe}: Rethinking Physical Consistency Evaluation in Generated Videos}, author = {Max Ku and Jiaojiao Fan and Zekun Hao and Francesco Ferroni and Heng Wang and Wenhu Chen and Ming-Yu Liu and Prithvijit Chattopadhyay}, year = {2026}, eprint = {2609.38377}, archiveprefix = {arXiv} } @inproceedings{chow2025physbench, title = {PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding}, author = {Chow, Wei and Mao, Jiageng and Li, Boyi and Seita, Daniel and Guizilini, Vitor and Wang, Yue}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{wang2025physctrl, title = {PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation}, author = {Wang, Chen and Chen, Chuhao and Huang, Yiming and Dou, Zhiyang and Liu, Yuan and Gu, Jiatao and Liu, Lingjie}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {167907--167932}, doi = {10.52202/085713-5598} } @misc{physeditworld2026, title = {PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models}, author = {Bin Hu and Yanwen Ma and Jiehui Huang and Ziliang Zhang and Haoning Wu and Ruicheng Zhang and Yaokun Li and Zijun Wang and Yuechen Zhang and Chun-Mei Tseng and Hanhui Li and Shengju Qian and Jun Zhou and Kaipeng Zhang and Xiaodan Liang and Jiaya Jia and Xiu Li}, year = {2026}, eprint = {2606.26694}, archiveprefix = {arXiv} } @inproceedings{chen2025physgen3d, title = {{PhysGen3D}: Crafting a Miniature Interactive World from a Single Image}, author = {Chen, Boyuan and Jiang, Hanxiao and Liu, Shaowei and Gupta, Saurabh and Li, Yunzhu and Zhao, Hao and Wang, Shenlong}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {6178--6189}, doi = {10.1109/cvpr52734.2025.00579} } @inproceedings{liu2024physgen, title = {{PhysGen}: Rigid-Body Physics-Grounded Image-to-Video Generation}, author = {Shaowei Liu and Zhongzheng Ren and Saurabh Gupta and Shenlong Wang}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, pages = {360--378}, doi = {10.1007/978-3-031-73007-8_21} } @misc{physicsmind2025, title = {PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models}, author = {Chak-Wing Mak and Guanyu Zhu and Boyi Zhang and Hongji Li and Xiaowei Chi and Kevin Zhang and Yichen Wu and Yangfan He and Chun-Kai Fan and Wentao Lu and Kuangzhi Ge and Xinyu Fang and Hongyang He and Kuan Lu and Tianxiang Xu and Li Zhang and Yongxin Ni and Youhua Li and Shanghang Zhang}, year = {2026}, eprint = {2601.16007}, archiveprefix = {arXiv} } @inproceedings{physion2021, title = {Physion: Evaluating Physical Prediction from Vision in Humans and Machines}, author = {Daniel M. Bear and Elias Wang and Damian Mrowca and Felix J. Binder and Hsiao-Yu Fish Tung and R. T. Pramod and Cameron Holdaway and Sirui Tao and Kevin Smith and Fan-Yun Sun and Li Fei-Fei and Nancy Kanwisher and Joshua B. Tenenbaum and Daniel L. K. Yamins and Judith E. Fan}, booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks}, year = {2021}, volume = {1}, } @inproceedings{tan2024physmotion, title = {{PhysMotion}: Physics-Grounded Dynamics from a Single Image}, author = {Tan, Xiyang and Jiang, Ying and Li, Xuan and Zong, Zeshun and Xie, Tianyi and Yang, Yin and Jiang, Chenfanfu}, booktitle = {2026 International Conference on 3D Vision (3DV)}, year = {2026}, pages = {806--818}, doi = {10.1109/3dv69130.2026.00082} } @inproceedings{physrag2026, title = {PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation}, author = {Cheng, Kexu and Liu, Zicheng and Gao, Mingju and Song, Chunhe and Tang, Hao}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {558--578}, doi = {10.1007/978-3-032-37429-5_32} } @inproceedings{gu2025phyworldbench, title = {$PhyWorldBench$: A Comprehensive Evaluation of Physical Realism in Text-to-Video Models}, author = {Gu, Jing and Liu, Xian and Zeng, Yu and Nagarajan, Ashwin and Zhu, Fangrui and Hong, Daniel and Fan, Yue and Yan, Qianqi and Zhou, Kaiwen and Liu, Ming-Yu and Wang, Xin Eric}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{wei2026pixelumm, title = {PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation}, author = {Cong Wei and Xuanchi Ren and Bryan Chu and Weiming Ren and Huan Ling and Jiahui Huang and Laura Leal-Taix\'e and Sanja Fidler and Wenhu Chen and Zian Wang and Jay Zhangjie Wu}, year = {2026}, eprint = {2609.38597}, archiveprefix = {arXiv} } @inproceedings{hao2024visualtokens, title = {Principles of Visual Tokens for Efficient Video Understanding}, author = {Hao, Xinyue and Li, Gen and Gowda, Shreyank N and Fisher, Robert B. and Huang, Jonathan and Arnab, Anurag and Sevilla-Lara, Laura}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {21254--21264}, doi = {10.1109/iccv51701.2025.01974} } @misc{shen2026proar, title = {{ProAR}: Learning Prospective Reasoning with Autoregressive Video Models}, author = {Linghui Shen and Tinghui Zhu and Sheng Zhang and Muhao Chen}, year = {2026}, eprint = {2610.03664}, archiveprefix = {arXiv} } @inproceedings{hertz2022prompttoprompt, title = {Prompt-to-Prompt Image Editing with Cross-Attention Control}, author = {Amir Hertz and Ron Mokady and Jay Tenenbaum and Kfir Aberman and Yael Pritch and Daniel Cohen-Or}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2023} } @misc{yang2026pseudounificationentropyprobingreveals, title = {Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models}, author = {Songlin Yang and Xianghao Kong and Anyi Rao}, year = {2026}, eprint = {2604.10949}, archiveprefix = {arXiv} } @inproceedings{jin2024pyramidflow, title = {Pyramidal Flow Matching for Efficient Video Generative Modeling}, author = {Yang Jin and Zhicheng Sun and Ningyuan Li and Kun Xu and Kun Xu and Hao Jiang and Nan Zhuang and Quzhe Huang and Yang Song and Yadong Mu and Zhouchen Lin}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{pyratok2026, title = {PyraTok: Language-Aligned Pyramidal Tokenizer for Video Understanding and Generation}, author = {Susladkar, Onkar and Prakash, Tushar and Juvekar, Adheesh and Nguyen, Kiet A. and Jang, Dong-Hwan and Dhillon, Inderjit S and Lourentzou, Ismini}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {37906--37917}, } @inproceedings{carreira2017quo, title = {Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset}, author = {Carreira, Joao and Zisserman, Andrew}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, pages = {6299--6308}, doi = {10.1109/cvpr.2017.502} } @misc{xu2025qwen25omni, title = {Qwen2.5-Omni Technical Report}, author = {Jin Xu and Zhifang Guo and Jinzheng He and Hangrui Hu and Ting He and Shuai Bai and Keqin Chen and Jialin Wang and Yang Fan and Kai Dang and Bin Zhang and Xiong Wang and Yunfei Chu and Junyang Lin}, year = {2025}, eprint = {2503.20215}, archiveprefix = {arXiv} } @misc{qwen25vl2025, title = {Qwen2.5-VL Technical Report}, author = {Shuai Bai and Keqin Chen and Xuejing Liu and Jialin Wang and Wenbin Ge and Sibo Song and Kai Dang and Peng Wang and Shijie Wang and Jun Tang and Humen Zhong and Yuanzhi Zhu and Mingkun Yang and Zhaohai Li and Jianqiang Wan and Pengfei Wang and Wei Ding and Zheren Fu and Yiheng Xu and Jiabo Ye and Xi Zhang and Tianbao Xie and Zesen Cheng and Hang Zhang and Zhibo Yang and Haiyang Xu and Junyang Lin}, year = {2025}, eprint = {2502.13923}, archiveprefix = {arXiv} } @misc{xu2025qwen3, title = {Qwen3-Omni Technical Report}, author = {Xu, Jin and Guo, Zhifang and Hu, Hangrui and Chu, Yunfei and Wang, Xiong and He, Jinzheng and Wang, Yuxuan and Shi, Xian and He, Ting and Zhu, Xinfa and Lv, Yuanjun and Wang, Yongqi and Guo, Dake and Wang, He and Ma, Linhan and Zhang, Pei and Zhang, Xinyu and Hao, Hongkun and Guo, Zishan and Yang, Baosong and Zhang, Bin and Ma, Ziyang and Wei, Xipin and Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Peng and Yang, Mingkun and Liu, Dayiheng and Ren, Xingzhang and Zheng, Bo and Men, Rui and Zhou, Fan and Yu, Bowen and Yang, Jianxin and Yu, Le and Zhou, Jingren and Lin, Junyang}, year = {2025}, eprint = {2509.17765}, archiveprefix = {arXiv} } @misc{bai2025qwen3, title = {Qwen3-VL Technical Report}, author = {Shuai Bai and Yuxuan Cai and Ruizhe Chen and Keqin Chen and Xionghui Chen and Zesen Cheng and Lianghao Deng and Wei Ding and Chang Gao and Chunjiang Ge and Wenbin Ge and Zhifang Guo and Qidong Huang and Jie Huang and Fei Huang and Binyuan Hui and Shutong Jiang and Zhaohai Li and Mingsheng Li and Mei Li and Kaixin Li and Zicheng Lin and Junyang Lin and Xuejing Liu and Jiawei Liu and Chenglong Liu and Yang Liu and Dayiheng Liu and Shixuan Liu and Dunjie Lu and Ruilin Luo and Chenxu Lv and Rui Men and Lingchen Meng and Xuancheng Ren and Xingzhang Ren and Sibo Song and Yuchong Sun and Jun Tang and Jianhong Tu and Jianqiang Wan and Peng Wang and Pengfei Wang and Qiuyue Wang and Yuxuan Wang and Tianbao Xie and Yiheng Xu and Haiyang Xu and Jin Xu and Zhibo Yang and Mingkun Yang and Jianxin Yang and An Yang and Bowen Yu and Fei Zhang and Hang Zhang and Xi Zhang and Bo Zheng and Humen Zhong and Jingren Zhou and Fan Zhou and Jing Zhou and Yuanzhi Zhu and Ke Zhu}, year = {2025}, eprint = {2511.21631}, archiveprefix = {arXiv} } @inproceedings{shi2026realunifyunifiedmodelstruly, title = {RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark}, author = {Shi, Yang and Dong, Yuhao and Ding, Yue and Wang, Yuran and Zhu, Xuanyu and Zhou, Sheng and Liu, Wenting and Tian, Haochen and Wang, Rundong and Wang, Huanqian and Liu, Zuyan and Zeng, Bohan and Chen, Ruizhe and Wang, Qixun and Zhang, Zhuoran and Chen, Xinlong and Tong, Chengzhuo and Li, Bozhou and Liu, Qiang and Wang, Haotian and Yang, Wenjing and Zhang, Yuanxing and Wan, Pengfei and Zhang, Yi-Fan and Liu, Ziwei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {22488--22497}, } @inproceedings{xie2026reconstruction, title = {Reconstruction Alignment Improves Unified Multimodal Models}, author = {Ji Xie and Trevor Darrell and Luke Zettlemoyer and XuDong Wang}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{ha2018worldmodels, title = {Recurrent World Models Facilitate Policy Evolution}, author = {Ha, David and Schmidhuber, J\"{u}rgen}, booktitle = {Advances in Neural Information Processing Systems}, year = {2018}, volume = {31}, } @misc{hong2025relic, title = {RELIC: Interactive Video World Model with Long-Horizon Memory}, author = {Yicong Hong and Yiqun Mei and Chongjian Ge and Yiran Xu and Yang Zhou and Sai Bi and Yannick Hold-Geoffroy and Mike Roberts and Matthew Fisher and Eli Shechtman and Kalyan Sunkavalli and Feng Liu and Zhengqi Li and Hao Tan}, year = {2025}, eprint = {2512.04040}, archiveprefix = {arXiv} } @article{nwoye2022rendezvous, title = {Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos}, author = {Nwoye, Chinedu Innocent and Yu, Tong and Gonzalez, Cristians and Seeliger, Barbara and Mascagni, Pietro and Mutter, Didier and Marescaux, Jacques and Padoy, Nicolas}, journal = {Medical Image Analysis}, year = {2022}, volume = {78}, pages = {102433}, doi = {10.1016/j.media.2022.102433} } @article{damen2022rescaling, title = {Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100}, author = {Damen, Dima and Doughty, Hazel and Farinella, Giovanni Maria and Furnari, Antonino and Kazakos, Evangelos and Ma, Jian and Moltisanti, Davide and Munro, Jonathan and Perrett, Toby and Price, Will and Wray, Michael}, journal = {International Journal of Computer Vision}, year = {2022}, volume = {130}, number = {1}, pages = {33--55}, doi = {10.1007/s11263-021-01531-2} } @article{bardes2024vjepa, title = {Revisiting Feature Prediction for Learning Visual Representations from Video}, author = {Adrien Bardes and Quentin Garrido and Jean Ponce and Xinlei Chen and Michael Rabbat and Yann LeCun and Mahmoud Assran and Nicolas Ballas}, journal = {Transactions on Machine Learning Research}, year = {2024}, issn = {2835-8856}, } @inproceedings{zhou2024robodreamer, title = {{R}obo{D}reamer: Learning Compositional World Models for Robot Imagination}, author = {Zhou, Siyuan and Du, Yilun and Chen, Jiaben and Li, Yandong and Yeung, Dit-Yan and Gan, Chuang}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {61885--61896}, } @inproceedings{shang2025roboscape, title = {RoboScape: Physics-Informed Embodied World Model}, author = {Shang, Yu and Zhang, Xin and Tang, Yinzhou and Jin, Lei and Gao, Chen and Wu, Wei and Li, Yong}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {63674--63698}, doi = {10.52202/085713-2138} } @misc{jiang2026robowmbench, title = {RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation}, author = {Feng Jiang and Yang Chen and Kyle Xu and Yuchen Liu and Haifeng Wang and Zhenhao Shen and Jasper Lu and Shengze Huang and Yuanfei Wang and Chen Xie and Ruihai Wu}, year = {2026}, eprint = {2604.19092}, archiveprefix = {arXiv} } @inproceedings{liu2025rollingforcing, title = {Rolling Forcing: Autoregressive Long Video Diffusion in Real Time}, author = {Liu, Kunhao and Hu, Wenbo and Xu, Jiale and Shan, Ying and Lu, Shijian}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{hu2026s2pd, title = {{S2PD}: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation}, author = {Jeffrey Hu and Daniel Olmeda Reino and Ayush Tewari}, year = {2026}, eprint = {2610.06847}, archiveprefix = {arXiv} } @inproceedings{zhang2023sadtalker, title = {{SadTalker}: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation}, author = {Zhang, Wenxuan and Cun, Xiaodong and Wang, Xuan and Zhang, Yong and Shen, Xi and Guo, Yu and Shan, Ying and Wang, Fei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {8652--8661}, doi = {10.1109/cvpr52729.2023.00836} } @inproceedings{jain2025sage, title = {SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning}, author = {Jain, Jitesh and blank, Allen AI and Li, Jialuo and Ma, Zixian and Zhang, Jieyu and Kim, Chris Dongjoo and Lee, Sangho and Tripathi, Rohun and Gupta, Tanmay and Clark, Christopher and Shi, Humphrey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {41478--41488}, } @inproceedings{ravi2024sam2, title = {SAM 2: Segment Anything in Images and Videos}, author = {Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and Rädle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Dollár, Piotr and Feichtenhofer, Christoph}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{chen2026sanavideo2, title = {{SANA-Video 2.0}: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation}, author = {Junsong Chen and Jincheng Yu and Yitong Li and Shuchen Xue and Haozhe Liu and Jingyu Xin and Yuyang Zhao and Tian Ye and Zhangjie Wu and Zian Wang and Daquan Zhou and Ping Luo and Song Han and Enze Xie}, year = {2026}, eprint = {2607.21553}, archiveprefix = {arXiv} } @inproceedings{sun2020waymo, title = {Scalability in Perception for Autonomous Driving: Waymo Open Dataset}, author = {Sun, Pei and Kretzschmar, Henrik and Dotiwalla, Xerxes and Chouard, Aurelien and Patnaik, Vijaysai and Tsui, Paul and Guo, James and Zhou, Yin and Chai, Yuning and Caine, Benjamin and Vasudevan, Vijay and Han, Wei and Ngiam, Jiquan and Zhao, Hang and Timofeev, Aleksei and Ettinger, Scott and Krivokon, Maxim and Gao, Amy and Joshi, Aditya and Zhang, Yu and Shlens, Jonathon and Chen, Zhifeng and Anguelov, Dragomir}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, pages = {2443--2451}, doi = {10.1109/cvpr42600.2020.00252} } @inproceedings{Peebles_2023_ICCV, title = {Scalable Diffusion Models with Transformers}, author = {Peebles, William and Xie, Saining}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {4195--4205}, doi = {10.1109/iccv51070.2023.00387} } @inproceedings{esser2024sd3, title = {Scaling Rectified Flow Transformers for High-Resolution Image Synthesis}, author = {Esser, Patrick and Kulal, Sumith and Blattmann, Andreas and Entezari, Rahim and M\"{u}ller, Jonas and Saini, Harry and Levi, Yam and Lorenz, Dominik and Sauer, Axel and Boesel, Frederic and Podell, Dustin and Dockhorn, Tim and English, Zion and Rombach, Robin}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {12606--12633}, } @inproceedings{chen2025longvilar1, title = {Scaling RL to Long Videos}, author = {Chen, Yukang and Huang, Wei and Shi, Baifeng and Hu, Qinghao and Ye, Hanrong and Zhu, Ligeng and Liu, Zhijian and Molchanov, Pavlo and Kautz, Jan and Qi, Xiaojuan and Liu, Sifei and Yin, Hongxu and Lu, Yao and Han, Song}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {172842--172870}, doi = {10.52202/085713-5753} } @inproceedings{zeng2025scenerag, title = {SceneRAG: Scene-Level Retrieval-Augmented Generation for Video Understanding}, author = {Zeng, Nianbo and Hou, Haowen and Yu, F. Richard and Shi, Si and He, Ying Tiffany}, booktitle = {ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year = {2026}, pages = {12122--12126}, doi = {10.1109/icassp55912.2026.11462022} } @inproceedings{zhao2026scp, title = {SCP: Spatial Causal Prediction in Video}, author = {Zhao, Yanguang and Yang, Jie and Wu, Shengqiong and Hu, Shutong and Qiu, Hongbo and Wang, Yu and Zhang, Guijia and Ze, Tan Kai and Fei, Hao and Lin, Chia-Wen and Lee, Mong-Li and Hsu, Wynne}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition -- Findings (CVPRF)}, year = {2026}, pages = {7168--7178}, doi = {10.1109/cvprf71909.2026.00688} } @inproceedings{meng2021sdedit, title = {{SDEdit}: Guided Image Synthesis and Editing with Stochastic Differential Equations}, author = {Chenlin Meng and Yutong He and Yang Song and Jiaming Song and Jiajun Wu and Jun-Yan Zhu and Stefano Ermon}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2022} } @misc{seedance2025, title = {Seedance 1.0: Exploring the Boundaries of Video Generation Models}, author = {Gao, Yu and Guo, Haoyuan and Hoang, Tuyen and Huang, Weilin and Jiang, Lu and Kong, Fangyuan and Li, Huixia and Li, Jiashi and Li, Liang and Li, Xiaojie and Li, Xunsong and Li, Yifu and Lin, Shanchuan and Lin, Zhijie and Liu, Jiawei and Liu, Shu and Nie, Xiaonan and Qing, Zhiwu and Ren, Yuxi and Sun, Li and Tian, Zhi and Wang, Rui and Wang, Sen and Wei, Guoqiang and Wu, Guohong and Wu, Jie and Xia, Ruiqi and Xiao, Fei and Xiao, Xuefeng and Yan, Jiangqiao and Yang, Ceyuan and Yang, Jianchao and Yang, Runkai and Yang, Tao and Yang, Yihang and Ye, Zilyu and Zeng, Xuejiao and Zeng, Yan and Zhang, Heng and Zhao, Yang and Zheng, Xiaozheng and Zhu, Peihao and Zou, Jiaxin and Zuo, Feilong}, year = {2025}, eprint = {2506.09113}, archiveprefix = {arXiv} } @misc{seedance2_2026, title = {{Seedance 2.0}: Advancing Video Generation for World Complexity}, author = {{Team Seedance} and De Chen and Liyang Chen and Xin Chen and others}, year = {2026}, eprint = {2604.14148}, archiveprefix = {arXiv} } @inproceedings{long2025m3agent, title = {Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory}, author = {Long, Lin and He, Yichen and Ye, Wentao and Pan, Yiyuan and Lin, Yuan and Li, Hang and Zhao, Junbo and Li, Wei}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{chen2023seine, title = {{SEINE}: Short-to-Long Video Diffusion Model for Generative Transition and Prediction}, author = {Chen, Xinyuan and Wang, Yaohui and Zhang, Lingjun and Zhuang, Shaobin and Ma, Xin and Yu, Jiashuo and Wang, Yali and Lin, Dahua and Qiao, Yu and Liu, Ziwei}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{selfforcing2025, title = {Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion}, author = {Huang, Xun and Li, Zhengqi and He, Guande and Zhou, Mingyuan and Shechtman, Eli}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {167283--167308}, doi = {10.52202/085713-5576} } @inproceedings{yu2023sevila, title = {Self-Chained Image-Language Model for Video Localization and Question Answering}, author = {Yu, Shoubin and Cho, Jaemin and Yadav, Prateek and Bansal, Mohit}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {76749--76771}, doi = {10.52202/075280-3354} } @inproceedings{chen2024sharegpt4video, title = {ShareGPT4Video: Improving Video Understanding and Generation with Better Captions}, author = {Chen, Lin and Wei, Xilin and Li, Jinsong and Dong, Xiaoyi and Zhang, Pan and Zang, Yuhang and Chen, Zehui and Duan, Haodong and Lin, Bin and Tang, Zhenyu and Yuan, Li and Qiao, Yu and Lin, Dahua and Zhao, Feng and Wang, Jiaqi}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {19472--19495}, doi = {10.52202/079017-0614} } @inproceedings{xie2025show, title = {Show-o2: Improved Native Unified Multimodal Models}, author = {Xie, Jinheng and Yang, Zhenheng and Shou, Mike Zheng}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {47490--47518}, doi = {10.52202/085713-1584} } @inproceedings{xie2024show, title = {Show-o: One Single Transformer to Unify Multimodal Understanding and Generation}, author = {Xie, Jinheng and Mao, Weijia and Bai, Zechen and Zhang, David Junhao and Wang, Weihao and Lin, Kevin Qinghong and Gu, Yuchao and Chen, Zhijie and Yang, Zhenheng and Shou, Mike Zheng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{tschannen2025siglip, title = {{SigLIP} 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features}, author = {Tschannen, Michael and Gritsenko, Alexey and Wang, Xiao and Naeem, Muhammad Ferjad and Alabdulmohsin, Ibrahim and Parthasarathy, Nikhil and Evans, Talfan and Beyer, Lucas and Xia, Ye and Mustafa, Basil and Hénaff, Olivier and Harmsen, Jeremiah and Steiner, Andreas and Zhai, Xiaohua}, year = {2025}, eprint = {2502.14786}, archiveprefix = {arXiv} } @inproceedings{zhai2023sigmoid, title = {Sigmoid Loss for Language Image Pre-Training}, author = {Zhai, Xiaohua and Mustafa, Basil and Kolesnikov, Alexander and Beyer, Lucas}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {11975--11986}, doi = {10.1109/iccv51070.2023.01100} } @inproceedings{feichtenhofer2019slowfast, title = {SlowFast Networks for Video Recognition}, author = {Feichtenhofer, Christoph and Fan, Haoqi and Malik, Jitendra and He, Kaiming}, booktitle = {Proceedings of the IEEE/CVF international conference on computer vision}, year = {2019}, pages = {6202--6211}, doi = {10.1109/iccv.2019.00630} } @inproceedings{deliege2021soccernetv2, title = {SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos}, author = {Deliege, Adrien and Cioppa, Anthony and Giancola, Silvio and Seikavandi, Meisam J. and Dueholm, Jacob V. and Nasrollahi, Kamal and Ghanem, Bernard and Moeslund, Thomas B. and Van Droogenbroeck, Marc}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)}, year = {2021}, pages = {4503--4514}, doi = {10.1109/cvprw53098.2021.00508} } @inproceedings{giancola2018soccernet, title = {SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos}, author = {Giancola, Silvio and Amine, Mohieddine and Dghaily, Tarek and Ghanem, Bernard}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops}, year = {2018}, pages = {1792--179210}, doi = {10.1109/cvprw.2018.00223} } @misc{solaris2026, title = {Solaris: Building a Multiplayer Video World Model in Minecraft}, author = {Georgy Savva and Oscar Michel and Daohan Lu and Suppakit Waiwitlikhit and Timothy Meehan and Dhairya Mishra and Srivats Poddar and Jack Lu and Saining Xie}, year = {2026}, eprint = {2602.22208}, archiveprefix = {arXiv} } @misc{huang2026solarwm, title = {SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models}, author = {Junchao Huang and Guian Fang and Shengju Qian and Xianghao Kong and Zhuoran Zhao and Wei Huang and Yihua Du and Zixin Zhang and Justin Cui and Yuchao Gu and Yukang Chen and Xinting Hu and Tianyu He and Shaoshuai Shi and Zhuotao Tian and Xin Wang and Mike Zheng Shou and Li Jiang}, year = {2026}, eprint = {2609.02886}, archiveprefix = {arXiv} } @misc{sora2_2025, title = {Sora 2 Is Here}, author = {{OpenAI}}, year = {2025}, howpublished = {OpenAI announcement} } @misc{yang2026smi, title = {Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory}, author = {Ying Yang and Guiyu Zhang and Lianghua Huang and Chang Nie and Chenyang Si and Haofan Wang and Shaoshuai Shi and Li Jiang}, year = {2026}, eprint = {2610.02521}, archiveprefix = {arXiv} } @inproceedings{qian2021cvrl, title = {Spatiotemporal Contrastive Video Representation Learning}, author = {Qian, Rui and Meng, Tianjian and Gong, Boqing and Yang, Ming-Hsuan and Wang, Huisheng and Belongie, Serge and Cui, Yin}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, pages = {6964--6974}, doi = {10.1109/cvpr46437.2021.00689} } @misc{blattmann2023stable, title = {Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets}, author = {Blattmann, Andreas and Dockhorn, Tim and Kulal, Sumith and Mendelevitch, Daniel and Kilian, Maciej and Lorenz, Dominik and Levi, Yam and English, Zion and Voleti, Vikram and Letts, Adam and Jampani, Varun and Rombach, Robin}, year = {2023}, eprint = {2311.15127}, archiveprefix = {arXiv} } @misc{stableworldmodel2026, title = {stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation}, author = {Lucas Maes and Quentin Le Lidec and Luiz Facury and Nassim Massaudi and Ayush Chaurasia and Francesco Capuano and Richard Gao and Taj Gillin and Dan Haramati and Damien Scieur and Yann LeCun and Randall Balestriero}, year = {2026}, eprint = {2605.21800}, archiveprefix = {arXiv} } @inproceedings{star2024, title = {STAR: A Benchmark for Situated Reasoning in Real-World Videos}, author = {Wu, Bo and Yu, Shoubin and Chen, Zhenfang and Tenenbaum, Joshua B. and Gan, Chuang}, booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks}, year = {2021}, volume = {1}, } @inproceedings{gu2025starflowv, title = {{STARFlow-V: End-to-End Video Generative Modeling with Autoregressive Normalizing Flows}}, author = {Gu, Jiatao and Shen, Ying and Chen, Tianrong and Dinh, Laurent and Wang, Yuyang and Bautista, Miguel Angel and Berthelot, David and Susskind, Josh and Zhai, Shuangfei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {9084--9094} } @misc{ma2025stepvideo, title = {Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model}, author = {Guoqing Ma and Haoyang Huang and Kun Yan and Liangyu Chen and Nan Duan and Shengming Yin and Changyi Wan and Ranchen Ming and Xiaoniu Song and Xing Chen and Yu Zhou and Deshan Sun and Deyu Zhou and Jian Zhou and Kaijun Tan and Kang An and Mei Chen and Wei Ji and Qiling Wu and Wen Sun and Xin Han and Yanan Wei and Zheng Ge and Aojie Li and Bin Wang and Bizhu Huang and Bo Wang and Brian Li and Changxing Miao and Chen Xu and Chenfei Wu and Chenguang Yu and Dapeng Shi and Dingyuan Hu and Enle Liu and Gang Yu and Ge Yang and Guanzhe Huang and Gulin Yan and Haiyang Feng and Hao Nie and Haonan Jia and Hanpeng Hu and Hanqi Chen and Haolong Yan and Heng Wang and Hongcheng Guo and Huilin Xiong and Huixin Xiong and Jiahao Gong and Jianchang Wu and Jiaoren Wu and Jie Wu and Jie Yang and Jiashuai Liu and Jiashuo Li and Jingyang Zhang and Junjing Guo and Junzhe Lin and Kaixiang Li and Lei Liu and Lei Xia and Liang Zhao and Liguo Tan and Liwen Huang and Liying Shi and Ming Li and Mingliang Li and Muhua Cheng and Na Wang and Qiaohui Chen and Qinglin He and Qiuyan Liang and Quan Sun and Ran Sun and Rui Wang and Shaoliang Pang and Shiliang Yang and Sitong Liu and Siqi Liu and Shuli Gao and Tiancheng Cao and Tianyu Wang and Weipeng Ming and Wenqing He and Xu Zhao and Xuelin Zhang and Xianfang Zeng and Xiaojia Liu and Xuan Yang and Yaqi Dai and Yanbo Yu and Yang Li and Yineng Deng and Yingming Wang and Yilei Wang and Yuanwei Lu and Yu Chen and Yu Luo and Yuchu Luo and Yuhe Yin and Yuheng Feng and Yuxiang Yang and Zecheng Tang and Zekai Zhang and Zidong Yang and Binxing Jiao and Jiansheng Chen and Jing Li and Shuchang Zhou and Xiangyu Zhang and Xinhao Zhang and Yibo Zhu and Heung-Yeung Shum and Daxin Jiang}, year = {2025}, eprint = {2502.10248}, archiveprefix = {arXiv} } @article{zhou2018stereomagnification, title = {Stereo Magnification: Learning View Synthesis Using Multiplane Images}, author = {Zhou, Tinghui and Tucker, Richard and Flynn, John and Fyffe, Graham and Snavely, Noah}, journal = {ACM Transactions on Graphics}, year = {2018}, volume = {37}, number = {4}, pages = {1--12}, doi = {10.1145/3197517.3201323} } @inproceedings{li2025stibench, title = {{STI-Bench}: Are {MLLMs} Ready for Precise Spatial-Temporal World Understanding?}, author = {Li, Yun and Zhang, Yiming and Lin, Tao and Liu, Xiangrui and Cai, Wenxiao and Liu, Zheng and Zhao, Bo}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {5622--5632}, doi = {10.1109/iccv51701.2025.00533} } @misc{lee2018savp, title = {Stochastic Adversarial Video Prediction}, author = {Lee, Alex X. and Zhang, Richard and Ebert, Frederik and Abbeel, Pieter and Finn, Chelsea and Levine, Sergey}, year = {2018}, eprint = {1804.01523}, archiveprefix = {arXiv} } @inproceedings{babaeizadeh2018sv2p, title = {Stochastic Variational Video Prediction}, author = {Mohammad Babaeizadeh and Chelsea Finn and Dumitru Erhan and Roy H. Campbell and Sergey Levine}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2018} } @inproceedings{kimstream, title = {STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models}, author = {Pum Jun Kim and Seojun Kim and Jaejun Yoo}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{xia2025streamo, title = {Streaming Video Instruction Tuning}, author = {Xia, Jiaer and Chen, Peixian and Zhang, Mengdan and Sun, Xing and Zhou, Kaiyang}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {31219--31229}, } @inproceedings{tang2026streamingeval, title = {StreamingEval: A Unified Evaluation Framework Towards Realistic Streaming Video Understanding}, author = {Guowei Tang and Tianwen Qian and Huanran Zheng and Yifei Wang and Xiaoling Wang}, booktitle = {Findings of the Association for Computational Linguistics: ACL 2026}, year = {2026}, pages = {5945--5960}, doi = {10.18653/v1/2026.findings-acl.295} } @inproceedings{henschel2025streamingt2v, title = {StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text}, author = {Henschel, Roberto and Khachatryan, Levon and Poghosyan, Hayk and Hayrapetyan, Daniil and Tadevosyan, Vahram and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {2568--2577}, doi = {10.1109/cvpr52734.2025.00245} } @inproceedings{xu2025streamingvlm, title = {StreamingVLM: Real-Time Understanding for Infinite Video Streams}, author = {Xu, Ruyi and Xiao, Guangxuan and Chen, Yukang and He, Liuning and Lu, Yao and Han, Song}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{zeng2025surgvlm, title = {SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence}, author = {Zhitao Zeng and Zhu Zhuo and Xiaojun Jia and Erli Zhang and Junde Wu and Jiaan Zhang and Yuxuan Wang and Chang Han Low and Jian Jiang and Zilong Zheng and Xiaochun Cao and Yutong Ban and Qi Dou and Yang Liu and Yueming Jin}, year = {2025}, eprint = {2506.02555}, archiveprefix = {arXiv} } @inproceedings{yang2025svbench, title = {{SVB}ench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding}, author = {Zhenyu Yang and Yuhang Hu and Zemin Du and Dizhan Xue and Shengsheng Qian and Jiahong Wu and Fan Yang and Weiming Dong and Changsheng Xu}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{liu2026svcbench, title = {SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance}, author = {Pengyiang Liu and Zhongyue Shi and Hongye Hao and Qi Fu and Xueting Bi and Siwei Zhang and Xiaoyang Hu and Zitian Wang and Linjiang Huang and Si Liu}, booktitle = {Computer Vision -- ECCV 2026}, year = {2026}, volume = {17012}, pages = {522--538}, doi = {10.1007/978-3-032-37044-0_29} } @inproceedings{t2avcompass2025, title = {{T}2{AV}-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation}, author = {Cao, Zhe and Wang, Tao and Wang, Jiaming and Wang, Yanghai and Zhang, Yuanxing and Wang, Jiahao and Chen, Jialu and Deng, Miao and Liao, Chenxi and Zhang, Yize and Guo, Yubin and Zhang, Zhaoxiang and Liu, Jiaheng}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {11536--11580}, } @inproceedings{mou2023t2iadapter, title = {T2I-Adapter: Learning Adapters to Dig Out More Controllable Ability for Text-to-Image Diffusion Models}, author = {Mou, Chong and Wang, Xintao and Xie, Liangbin and Wu, Yanze and Zhang, Jian and Qi, Zhongang and Shan, Ying}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2024}, volume = {38}, number = {5}, pages = {4296--4304}, doi = {10.1609/aaai.v38i5.28226} } @inproceedings{sun2025t2vcompbenchcomprehensivebenchmarkcompositional, title = {T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-Video Generation}, author = {Sun, Kaiyue and Huang, Kaiyi and Liu, Xian and Wu, Yue and Xu, Zihan and Li, Zhenguo and Liu, Xihui}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {8406--8416}, doi = {10.1109/cvpr52734.2025.00787} } @inproceedings{charadessta2017, title = {TALL: Temporal Activity Localization via Language Query}, author = {Gao, Jiyang and Sun, Chen and Yang, Zhenheng and Nevatia, Ram}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, year = {2017}, pages = {5267--5275}, doi = {10.1109/iccv.2017.563} } @inproceedings{esser2021taming, title = {Taming Transformers for High-Resolution Image Synthesis}, author = {Esser, Patrick and Rombach, Robin and Ommer, Bjorn}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, pages = {12873--12883}, doi = {10.1109/cvpr46437.2021.01268} } @inproceedings{liu2024tempcompass, title = {TempCompass: Do Video LLMs Really Understand Videos?}, author = {Liu, Yuanxin and Li, Shicheng and Liu, Yi and Wang, Yuxiang and Ren, Shuhuai and Li, Lei and Chen, Sishuo and Sun, Xu and Hou, Lu}, booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2024}, year = {2024}, pages = {8731--8772}, doi = {10.18653/v1/2024.findings-acl.517} } @misc{ok2025tempcore, title = {{TempCore}: Are Video {QA} Benchmarks Temporally Grounded?}, author = {Hyunjong Ok and Jaeho Lee}, year = {2025}, eprint = {2509.01167}, archiveprefix = {arXiv} } @misc{temporalbench2024, title = {TemporalBench: Benchmarking Fine-Grained Temporal Understanding for Multimodal Video Models}, author = {Mu Cai and Reuben Tan and Jianrui Zhang and Bocheng Zou and Kai Zhang and Feng Yao and Fangrui Zhu and Jing Gu and Yiwu Zhong and Yuzhang Shang and Yao Dou and Jaden Park and Jianfeng Gao and Yong Jae Lee and Jianwei Yang}, year = {2024}, eprint = {2410.10818}, archiveprefix = {arXiv} } @inproceedings{yan2023teco, title = {Temporally Consistent Transformers for Video Generation}, author = {Yan, Wilson and Hafner, Danijar and James, Stephen and Abbeel, Pieter}, booktitle = {International Conference on Machine Learning}, year = {2023}, volume = {202}, pages = {39062--39098}, } @inproceedings{jang2017tgif, title = {TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering}, author = {Jang, Yunseok and Song, Yale and Yu, Youngjae and Kim, Youngjin and Kim, Gunhee}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2017}, pages = {2758--2766}, doi = {10.1109/cvpr.2017.149} } @inproceedings{goyal2017something, title = {The "Something Something" Video Database for Learning and Evaluating Visual Common Sense}, author = {Goyal, Raghav and Kahou, Samira Ebrahimi and Michalski, Vincent and Materzynska, Joanna and Westphal, Susanne and Kim, Heuna and Haenel, Valentin and Fruend, Ingo and Yianilos, Peter and Mueller-Freitag, Moritz and Hoppe, Florian and Thurau, Christian and Bax, Ingo and Memisevic, Roland}, booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)}, year = {2017}, pages = {5842--5850}, doi = {10.1109/iccv.2017.622} } @misc{davis2017, title = {The 2017 DAVIS Challenge on Video Object Segmentation}, author = {Jordi Pont-Tuset and Federico Perazzi and Sergi Caelles and Pablo Arbeláez and Alex Sorkine-Hornung and Luc Van Gool}, year = {2017}, eprint = {1704.00675}, archiveprefix = {arXiv} } @misc{kay2017kinetics, title = {The Kinetics Human Action Video Dataset}, author = {Will Kay and Joao Carreira and Karen Simonyan and Brian Zhang and Chloe Hillier and Sudheendra Vijayanarasimhan and Fabio Viola and Tim Green and Trevor Back and Paul Natsev and Mustafa Suleyman and Andrew Zisserman}, year = {2017}, eprint = {1705.06950}, archiveprefix = {arXiv} } @article{idrees2017thumos, title = {The THUMOS Challenge on Action Recognition for Videos ``in the Wild''}, author = {Idrees, Haroon and Zamir, Amir R. and Jiang, Yu-Gang and Gorban, Alex and Laptev, Ivan and Sukthankar, Rahul and Shah, Mubarak}, journal = {Computer Vision and Image Understanding}, year = {2017}, volume = {155}, pages = {1--23}, doi = {10.1016/j.cviu.2016.10.018} } @inproceedings{zhang2018unreasonableeffectivenessdeepfeatures, title = {The Unreasonable Effectiveness of Deep Features As a Perceptual Metric}, author = {Zhang, Richard and Isola, Phillip and Efros, Alexei A. and Shechtman, Eli and Wang, Oliver}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2018}, pages = {586--595}, doi = {10.1109/cvpr.2018.00068} } @inproceedings{wang2026thinkverify, title = {Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding}, author = {Wang, Zheng and Chen, Haoran and Qin, Haoxuan and Wei, Zhipeng and Qian, Tianwen and Bai, Cong}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {33784--33793}, } @inproceedings{vsibench2024, title = {Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces}, author = {Yang, Jihan and Yang, Shusheng and Gupta, Anjali W. and Han, Rilyn and Fei-Fei, Li and Xie, Saining}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {10632--10643}, doi = {10.1109/cvpr52734.2025.00994} } @inproceedings{tong2026thinkingvideovideogeneration, title = {Thinking with Video: Video Generation As a Promising Multimodal Reasoning Paradigm}, author = {Tong, Jingqi and Mou, Yurong and Li, Hangcheng and Li, Mingzhe and Yang, Yongzhuo and Zhang, Ming and Chen, Qiguang and Liang, Tianyi and Hu, Xiaomeng and Zheng, Yining and Chen, Xinchi and Zhao, Jun and Huang, Xuanjing and Qiu, Xipeng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {41121--41129}, } @inproceedings{wang2025timer1, title = {Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding}, author = {Wang, Ye and Wang, Ziheng and Xu, Boshen and Du, Yang and Lin, Kejun and Xiao, Zihan and Yue, Zihao and Ju, Jianzhong and Zhang, Liang and Yang, Dingyi and Fang, Xiangnan and He, Zewen and Luo, Zhenbo and Wang, Wenxuan and Lin, Junqi and Luan, Jian and Jin, Qin}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {83330--83364}, doi = {10.52202/085713-2793} } @misc{li2026timeblind, title = {TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs}, author = {Baiqi Li and Kangyi Zhao and Ce Zhang and Chancharik Mitra and Jean de Dieu Nyandwi and Gedas Bertasius}, year = {2026}, eprint = {2602.00288}, archiveprefix = {arXiv} } @inproceedings{ren2024timechat, title = {TimeChat: A Time-Sensitive Multimodal Large Language Model for Long Video Understanding}, author = {Ren, Shuhuai and Yao, Linli and Li, Shicheng and Sun, Xu and Hou, Lu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {14313--14323}, doi = {10.1109/cvpr52733.2024.01357} } @inproceedings{liu2024teacache, title = {Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model}, author = {Liu, Feng and Zhang, Shiwei and Wang, Xiaofeng and Wei, Yujie and Qiu, Haonan and Zhao, Yuzhong and Zhang, Yingya and Ye, Qixiang and Wan, Fang}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {7353--7363}, doi = {10.1109/cvpr52734.2025.00689} } @inproceedings{geyer2023tokenflow, title = {{TokenFlow}: Consistent Diffusion Features for Consistent Video Editing}, author = {Michal Geyer and Omer Bar-Tal and Shai Bagon and Tali Dekel}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @misc{luo2026torchummunifiedmultimodalmodel, title = {TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-Training}, author = {Yinyi Luo and Wenwen Wang and Hayes Bai and Hongyu Zhu and Hao Chen and Pan He and Marios Savvides and Sharon Li and Jindong Wang}, year = {2026}, eprint = {2604.10784}, archiveprefix = {arXiv} } @misc{unterthiner2019accurategenerativemodelsvideo, title = {Towards Accurate Generative Models of Video: A New Metric \& Challenges}, author = {Thomas Unterthiner and Sjoerd van Steenkiste and Karol Kurach and Raphael Marinier and Marcin Michalski and Sylvain Gelly}, year = {2018}, eprint = {1812.01717}, archiveprefix = {arXiv} } @misc{yang2025streamagent, title = {Towards Anticipatory Agents for Streaming Video Understanding}, author = {Haolin Yang and Feilong Tang and Lingxiao Zhao and Xinlin Zhuang and Yifan Lu and Xiang An and Ming Hu and Xiaofeng Zhang and Abdalla Swikir and Junjun He and Zongyuan Ge and Muhammad Haris Khan and Imran Razzak}, year = {2025}, eprint = {2508.01875}, archiveprefix = {arXiv} } @inproceedings{zhou2018youcook2, title = {Towards Automatic Learning of Procedures from Web Instructional Videos}, author = {Zhou, Luowei and Xu, Chenliang and Corso, Jason}, booktitle = {AAAI Conference on Artificial Intelligence}, year = {2018}, doi = {10.1609/aaai.v32i1.12342} } @misc{liu2026interactivevideoworld, title = {Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends}, author = {Jiuming Liu and Chaojun Ni and Mengmeng Liu and Chensheng Peng and Fangjinhua Wang and Sitian Shen and Marc Pollefeys and Masayoshi Tomizuka and Ayush Tewari and Per Ola Kristensson}, year = {2026}, eprint = {2606.01164}, archiveprefix = {arXiv} } @misc{liu2025revise, title = {Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning}, author = {Xinyu Liu and Hangjie Yuan and Yujie Wei and Jiazheng Xing and Yujin Han and Jiahao Pan and Yanbiao Ma and Chi-Min Chan and Kang Zhao and Shiwei Zhang and Wenhan Luo and Yike Guo}, year = {2025}, eprint = {2512.09924}, archiveprefix = {arXiv} } @inproceedings{meng2024phygenbench, title = {Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation}, author = {Meng, Fanqing and Liao, Jiaqi and Tan, Xinyu and Lu, Quanfeng and Shao, Wenqi and Zhang, Kaipeng and Cheng, Yu and Li, Dianqi and Luo, Ping}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {43781--43806}, } @misc{ma2026trace, title = {{TRACE}: Temporal Audit and Condition-Aware Evaluation of Streaming Video Understanding}, author = {Yibo Ma and Qianqian Zhang and Peng Liu and Tiancheng Zhao}, year = {2026}, eprint = {2609.30670}, archiveprefix = {arXiv} } @inproceedings{cheng2023deva, title = {Tracking Anything with Decoupled Video Segmentation}, author = {Cheng, Ho Kei and Oh, Seoung Wug and Price, Brian and Schwing, Alexander and Lee, Joon-Young}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {1316--1326}, doi = {10.1109/iccv51070.2023.00127} } @misc{hafner2025dreamer4, title = {Training Agents Inside of Scalable World Models}, author = {Danijar Hafner and Wilson Yan and Timothy Lillicrap}, year = {2025}, eprint = {2509.24527}, archiveprefix = {arXiv} } @inproceedings{ouyang2022training, title = {Training Language Models to Follow Instructions with Human Feedback}, author = {Ouyang, Long and Wu, Jeff and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll L. and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and Schulman, John and Hilton, Jacob and Kelton, Fraser and Miller, Luke and Simens, Maddie and Askell, Amanda and Welinder, Peter and Christiano, Paul and Leike, Jan and Lowe, Ryan}, booktitle = {Advances in Neural Information Processing Systems}, year = {2022}, volume = {35}, pages = {27730--27744}, doi = {10.52202/068431-2011} } @misc{zhang2026wrop, title = {Training Object Permanence in World Models}, author = {Haotian Zhang and Fengyuan Yu and Dezhi Luo and Haoran Sun and Zehong Zhao and Qingying Gao and Yihan Li and Siyuan An and Huayi Qin and Yilan Zhang and Zhengze Jiang and Pinyuan Feng and Renrui Zhang and Ziyu Guo and Letian Wang and Mengyue Yang and Kangfu Mei and Maijunxian Wang and Ran Ji and Vikash Kumar and Freda Shi and Chandra Sripada and Vincent C. Muller and Philip Torr and Alan Yuille and Nikolaus Kriegeskorte and Felix Juefei-Xu and Lvmin Zhang and Jieneng Chen and Yilun Du and Hokin Deng}, year = {2026}, eprint = {2609.28654}, archiveprefix = {arXiv} } @misc{pan2025transfer, title = {Transfer Between Modalities with {MetaQueries}}, author = {Pan, Xichen and Shukla, Satya Narayan and Singh, Aashu and Zhao, Zhuokai and Mishra, Shlok Kumar and Wang, Jialiang and Xu, Zhiyang and Chen, Jiuhai and Li, Kunpeng and Juefei-Xu, Felix and Hou, Ji and Xie, Saining}, year = {2025}, eprint = {2504.06256}, archiveprefix = {arXiv} } @inproceedings{zhou2024transfusion, title = {Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model}, author = {Chunting Zhou and Lili Yu and Arun Babu and Kushal Tirumala and Michihiro Yasunaga and Leonid Shamis and Jacob Kahn and Xuezhe Ma and Luke Zettlemoyer and Omer Levy}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @misc{motamed2025travl, title = {TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility}, author = {Saman Motamed and Minghao Chen and Luc Van Gool and Iro Laina}, year = {2025}, eprint = {2510.07550}, archiveprefix = {arXiv} } @inproceedings{lambert2025tulu3pushingfrontiers, title = {Tulu 3: Pushing Frontiers in Open Language Model Post-Training}, author = {Nathan Lambert and Jacob Morrison and Valentina Pyatkin and Shengyi Huang and Hamish Ivison and Faeze Brahman and Lester James V. Miranda and Alisa Liu and Nouha Dziri and Xinxi Lyu and Yuling Gu and Saumya Malik and Victoria Graf and Jena D. Hwang and Jiangjiang Yang and Ronan Le Bras and Oyvind Tafjord and Chris Wilhelm and Luca Soldaini and Noah A. Smith and Yizhong Wang and Pradeep Dasigi and Hannaneh Hajishirzi}, booktitle = {Conference on Language Modeling}, year = {2025} } @inproceedings{liu2025tuna, title = {TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models}, author = {Liu, Zhiheng and Ren, Weiming and Liu, Haozhe and Zhou, Zijian and Chen, Shoufa and Qiu, Haonan and Huang, Xiaoke and An, Zhaochong and Yang, Fanny and Patel, Aditya and Atliha, Viktar and Ng, Tony and Han, Xiao and Zhu, Chuyan and Zhang, Chenyang and Liu, Ding and Perez-Rua, Juan-Manuel and He, Sen and Schmidhuber, J\"urgen and Chen, Wenhu and Luo, Ping and Liu, Wei and Xiang, Tao and Schult, Jonas and Cong, Yuren}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {15740--15751}, } @inproceedings{wu2023tune, title = {Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation}, author = {Wu, Jay Zhangjie and Ge, Yixiao and Wang, Xintao and Lei, Stan Weixian and Gu, Yuchao and Shi, Yufei and Hsu, Wynne and Shan, Ying and Qie, Xiaohu and Shou, Mike Zheng}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {7623--7633}, doi = {10.1109/iccv51070.2023.00701} } @misc{turbodiffusion2025, title = {TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times}, author = {Zhang, Jintao and Zheng, Kaiwen and Jiang, Kai and Wang, Haoxu and Stoica, Ion and Gonzalez, Joseph E. and Chen, Jianfei and Zhu, Jun}, year = {2025}, eprint = {2512.16093}, archiveprefix = {arXiv} } @inproceedings{han2025tv2tv, title = {TV2TV: A Unified Framework for Interleaved Language and Video Generation}, author = {Han, Xiaochuang and Emad, Youssef and Hall, Melissa and Nguyen, John and Padthe, Karthik and Robbins, Liam and Bar, Amir and Chen, Delong and Drozdzal, Michal and Elbayad, Maha and Hu, Yushi and Li, Shang-Wen and Verbeek, Jakob and Wang, XuDong and Ghazvininejad, Marjan and Zettlemoyer, Luke and Dinan, Emily}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {7695--7706}, } @inproceedings{lei-etal-2018-tvqa, title = {TVQA: Localized, Compositional Video Question Answering}, author = {Lei, Jie and Yu, Licheng and Bansal, Mohit and Berg, Tamara}, booktitle = {Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing}, year = {2018}, pages = {1369--1379}, doi = {10.18653/v1/D18-1167} } @inproceedings{causal2needles2025, title = {Two Causally Related Needles in a Video Haystack}, author = {Li, Miaoyu and Chao, Qin and Li, Boyang}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, doi = {10.52202/085713-5584} } @misc{soomro2012ucf101, title = {UCF101: A Dataset of 101 Human Actions Classes from Videos in the Wild}, author = {Khurram Soomro and Amir Roshan Zamir and Mubarak Shah}, year = {2012}, eprint = {1212.0402}, archiveprefix = {arXiv} } @inproceedings{xue2025ultravideo, title = {UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions}, author = {Xue, Zhucun and Zhang, Jiangning and Hu, Teng and He, Haoyang and Chen, Yinan and Cai, Yuxuan and Wang, Yabiao and Wang, Chengjie and Liu, Yong and Li, Xiangtai and Tao, Dacheng}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, doi = {10.52202/085713-5445} } @article{ding2024worldmodelsurvey, title = {Understanding World or Predicting Future? A Comprehensive Survey of World Models}, author = {Ding, Jingtao and Zhang, Yunke and Shang, Yu and Zhang, Yuheng and Zong, Zefang and Feng, Jie and Yuan, Yuan and Su, Hongyuan and Li, Nian and Sukiennik, Nicholas and Xu, Fengli and Li, Yong}, journal = {ACM Computing Surveys}, year = {2026}, volume = {58}, number = {3}, pages = {1--38}, doi = {10.1145/3746449} } @inproceedings{zou2026unimmmumassivemultidisciplinemultimodal, title = {Uni-{MMMU}: A Massive Multi-Discipline Multimodal Unified Benchmark}, author = {Zou, Kai and Huang, Ziqi and Dong, Yuhao and Tian, Shulin and Zheng, Dian and Liu, Hongbo and He, Jingwen and Liu, Bin and Qiao, Yu and Liu, Ziwei}, booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2026}, pages = {908--924}, doi = {10.18653/v1/2026.acl-long.40}, } @misc{qin2026univigu, title = {Uni-ViGU: Towards Unified Video Generation and Understanding via a Diffusion-Based Video Generator}, author = {Luozheng Qin and Jia Gong and Qian Qiao and Tianjiao Li and Li Xu and Haoyu Pan and Chao Qu and Zhiyu Tan and Hao Li}, year = {2026}, eprint = {2604.08121}, archiveprefix = {arXiv} } @inproceedings{han2026unicorn, title = {{U}ni{C}orn: Towards Self-Improving Unified Multimodal Models Through Self-Generated Supervision}, author = {Fang, Zhen and Han, Ruiyan and Sun, XinYu and Ma, Yuchen and Wang, Ziheng and Zeng, Yu and Chen, Zehui and Chen, Lin and Huang, Wenxuan and Xu, Wei-Jie and Cao, Yi and Zhao, Feng}, booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2026}, pages = {13638--13669}, doi = {10.18653/v1/2026.acl-long.621}, } @inproceedings{unic2025, title = {Unified In-Context Video Editing}, author = {Ye, Zixuan and He, Xuanhua and Liu, Quande and Wang, Qiulin and Wang, Xintao and Wan, Pengfei and Zhang, Di and Gai, Kun and Chen, Qifeng and Luo, Wenhan}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{zhao2026unifiedmultimodalunderstandinggeneration, title = {Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities}, author = {Shanshan Zhao and Xinjie Zhang and Jintao Guo and Jiakui Hu and Lunhao Duan and Minghao Fu and Yong Xien Chng and Guo-Hua Wang and Qing-Guo Chen and Zhao Xu and Weihua Luo and Kaifu Zhang}, year = {2025}, eprint = {2505.02567}, archiveprefix = {arXiv} } @misc{wang2026unifiedreward, title = {Unified Reward Model for Multimodal Understanding and Generation}, author = {Yibin Wang and Yuhang Zang and Hao Li and Cheng Jin and Jiaqi Wang}, year = {2025}, eprint = {2503.05236}, archiveprefix = {arXiv} } @misc{wen2026unig2ubenchunifiedmodelsadvance, title = {UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?}, author = {Zimo Wen and Boxiu Li and Wanbo Zhang and Junxiang Lei and Xiaoyu Chen and Yijia Fan and Qi Zhang and Yujiang Wang and Lili Qiu and Bo Li and Ziwei Liu and Caihua Shan and Yifan Yang and Yifei Shen}, year = {2026}, eprint = {2603.03241}, archiveprefix = {arXiv} } @inproceedings{li2026unimunifiedanytoanyinterleaved, title = {UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark}, author = {Li, Yanlin and Guo, Minghui and Zhang, Kaiwen and Zhang, Shize and Zhao, Yiran and Li, Haodong and Zhou, Congyue and Zheng, Weijie and Yan, Yushen and Wu, Shengqiong and Ji, Wei and Cui, Lei and Wei, Furu and Fei, Hao and Lee, Mong-Li and Hsu, Wynne}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {15902--15911}, } @misc{lee2026unisafecomprehensivebenchmarksafety, title = {UniSAFE: A Comprehensive Benchmark for Safety Evaluation of Unified Multimodal Models}, author = {Segyu Lee and Boryeong Cho and Hojung Jung and Seokhyun An and Juhyeong Kim and Jaehyun Kwak and Yongjin Yang and Sangwon Jang and Youngrok Park and Wonjun Chang and Se-Young Yun}, year = {2026}, eprint = {2603.17476}, archiveprefix = {arXiv} } @inproceedings{huang2025unityvideounifiedmultimodalmultitask, title = {UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation}, author = {Huang, Jiehui and Zhang, Yuechen and He, Xu and Gao, Yuan and Cen, Zhi and Xia, Bin and Zhou, Yan and Tao, Xin and Wan, Pengfei and Jia, Jiaya}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {4471--4481}, } @misc{lu2025uniugp, title = {UniUGP: Unifying Understanding, Generation, and Planing for End-to-End Autonomous Driving}, author = {Hao Lu and Ziyang Liu and Guangfeng Jiang and Yuanfei Luo and Sheng Chen and Yangang Zhang and Ying-Cong Chen}, year = {2025}, eprint = {2512.09864}, archiveprefix = {arXiv} } @misc{liang2025univa, title = {UniVA: Universal Video Agent Towards Open-Source Next-Generation Video Generalist}, author = {Zhengyang Liang and Daoan Zhang and Huichi Zhou and Rui Huang and Bobo Li and Yuechen Zhang and Shengqiong Wu and Xiaohan Wang and Jiebo Luo and Lizi Liao and Hao Fei}, year = {2025}, eprint = {2511.08521}, archiveprefix = {arXiv} } @inproceedings{wei2026univbenchunifiedevaluationvideo, title = {UniVBench: Towards Unified Evaluation for Video Foundation Models}, author = {Wei, Jianhui and Zhang, Xiaotian and Li, Yichen and Wang, Yuan and Zhang, Yan and Chen, Ziyi and Tang, Zhihang and Xu, Wei and Liu, Zuozhu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {25654--25666}, } @inproceedings{bansal2023universalguidance, title = {Universal Guidance for Diffusion Models}, author = {Bansal, Arpit and Chu, Hong-Min and Schwarzschild, Avi and Sengupta, Soumyadip and Goldblum, Micah and Geiping, Jonas and Goldstein, Tom}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @misc{luo2025univid, title = {UniVid: The Open-Source Unified Video Model}, author = {Jiabin Luo and Junhui Lin and Zeyu Zhang and Biao Wu and Meng Fang and Ling Chen and Hao Tang}, year = {2025}, eprint = {2509.24200}, archiveprefix = {arXiv} } @inproceedings{univideo2025, title = {UniVideo: Unified Understanding, Generation, and Editing for Videos}, author = {Wei, Cong and Liu, Quande and Ye, Zixuan and Wang, Qiulin and Wang, Xintao and Wan, Pengfei and Gai, Kun and Chen, Wenhu}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{luo2020univl, title = {UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation}, author = {Huaishao Luo and Lei Ji and Botian Shi and Haoyang Huang and Nan Duan and Tianrui Li and Jason Li and Taroon Bharti and Ming Zhou}, year = {2020}, eprint = {2002.06353}, archiveprefix = {arXiv} } @misc{chen2026uniwam, title = {UniWAM: Unified World-Action Model}, author = {Wenxuan Song and Jiayi Chen and Jingbo Wang and Shuai Zhou and Xicheng Gong and Zehua Fan and Ziyang Zhou and Junwu E and Haodong Yan and Fuhao Li and Qize Yu and Xu Huang and Pengwei Wang and Wen Chen and Shunbo Zhou and Haoang Li}, year = {2026}, eprint = {2610.02054}, archiveprefix = {arXiv} } @inproceedings{lin2025videomarathon, title = {Unleashing Hour-Scale Video Training for Long Video-Language Understanding}, author = {Lin, Jingyang and Wu, Jialian and Sun, Ximeng and Wang, Ze and Liu, Jiang and Su, Yusheng and Yu, Xiaodong and Chen, Hao and Luo, Jiebo and Liu, Zicheng and Barsoum, Emad}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {17523--17552}, doi = {10.52202/085713-0591} } @inproceedings{wu2023gr1, title = {Unleashing Large-Scale Video Generative Pre-Training for Visual Robot Manipulation}, author = {Wu, Hongtao and Jing, Ya and Cheang, Chilam and Chen, Guangzeng and Xu, Jiafeng and Li, Xinghang and Liu, Minghuan and Li, Hang and Kong, Tao}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024} } @inproceedings{li2023unmasked, title = {Unmasked Teacher: Towards Training-Efficient Video Foundation Models}, author = {Li, Kunchang and Wang, Yali and Li, Yizhuo and Wang, Yi and He, Yinan and Wang, Limin and Qiao, Yu}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {19948--19960}, doi = {10.1109/iccv51070.2023.01826} } @inproceedings{luo2026unveiling, title = {Unveiling the Cognitive Compass: Theory-of-Mind-Guided Multimodal Emotion Reasoning}, author = {Luo, Meng and Li, Bobo and Xu, Shanqing and Zhang, Shize and Chen, Qiuchan and Han, Menglu and Chen, Wenhao and Huang, Yanxiang and Fei, Hao and Lee, Mong-Li and Hsu, Wynne}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{seo2020urvos, title = {URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark}, author = {Seonguk Seo and Joon-Young Lee and Bohyung Han}, booktitle = {Computer Vision -- ECCV 2020}, year = {2020}, pages = {208--223}, doi = {10.1007/978-3-030-58555-6_13} } @inproceedings{muckley2026vjepa21, title = {V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning}, author = {Lorenzo Mur-Labadia and Matthew Muckley and Amir Bar and Mido Assran and Koustuv Sinha and Mike Rabbat and Yann LeCun and Nicolas Ballas}, booktitle = {Computer Vision -- ECCV 2026}, year = {2026}, volume = {17005}, pages = {671--689}, doi = {10.1007/978-3-032-37369-4_36} } @misc{assran2025vjepa2, title = {V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning}, author = {Mido Assran and Adrien Bardes and David Fan and Quentin Garrido and Russell Howes and Mojtaba Komeili and Matthew Muckley and Ammar Rizvi and Claire Roberts and Koustuv Sinha and Artem Zholus and Sergio Arnaud and Abha Gejji and Ada Martin and Francois Robert Hogan and Daniel Dugas and Piotr Bojanowski and Vasil Khalidov and Patrick Labatut and Francisco Massa and Marc Szafraniec and Kapil Krishnakumar and Yong Li and Xiaodong Ma and Sarath Chandar and Franziska Meier and Yann LeCun and Michael Rabbat and Nicolas Ballas}, year = {2025}, eprint = {2506.09985}, archiveprefix = {arXiv} } @misc{guo2026vrae, title = {{V-RAE}: Rethinking Video Latent Spaces for Generation}, author = {Minghui Guo and Shengqiong Wu and Hao Fei}, year = {2026}, eprint = {2608.13556}, archiveprefix = {arXiv} } @misc{liu2026v2vbench, title = {{V2V-Bench}: A Comprehensive Benchmark for Video-to-Video Generation Evaluation}, author = {Tao Liu and Leela Krishna and Gouti Pavan Kumar and Sreeja K and Vishav Garg}, year = {2026}, eprint = {2606.05665}, archiveprefix = {arXiv} } @inproceedings{jiang2025vace, title = {VACE: All-in-One Video Creation and Editing}, author = {Jiang, Zeyinzi and Han, Zhen and Mao, Chaojie and Zhang, Jingfeng and Pan, Yulin and Liu, Yu}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {17191--17202}, doi = {10.1109/iccv51701.2025.01597} } @inproceedings{wang2019vatex, title = {VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research}, author = {Wang, Xin and Wu, Jiawei and Chen, Junkun and Li, Lei and Wang, Yuan-Fang and Wang, William Yang}, booktitle = {Proceedings of the IEEE/CVF international conference on computer vision}, year = {2019}, pages = {4581--4591}, doi = {10.1109/iccv.2019.00468} } @article{huang2024vbenchpp, title = {{VBench++}: Comprehensive and Versatile Benchmark Suite for Video Generative Models}, author = {Huang, Ziqi and Zhang, Fan and Xu, Xiaojie and He, Yinan and Yu, Jiashuo and Dong, Ziyue and Ma, Qianli and Chanpaisit, Nattapol and Si, Chenyang and Jiang, Yuming and Wang, Yaohui and Chen, Xinyuan and Chen, Ying-Cong and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, year = {2026}, volume = {48}, number = {3}, pages = {3268--3285}, doi = {10.1109/tpami.2025.3633890} } @misc{zheng2025vbench20advancingvideogeneration, title = {VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness}, author = {Dian Zheng and Ziqi Huang and Hongbo Liu and Kai Zou and Yinan He and Fan Zhang and Lulu Gu and Yuanhan Zhang and Jingwen He and Wei-Shi Zheng and Yu Qiao and Ziwei Liu}, year = {2025}, eprint = {2503.21755}, archiveprefix = {arXiv} } @inproceedings{huang2023vbenchcomprehensivebenchmarksuite, title = {VBench: Comprehensive Benchmark Suite for Video Generative Models}, author = {Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and Wang, Yaohui and Chen, Xinyuan and Wang, Limin and Lin, Dahua and Qiao, Yu and Liu, Ziwei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {21807--21818}, doi = {10.1109/cvpr52733.2024.02060} } @inproceedings{yang2024vca, title = {VCA: Video Curious Agent for Long Video Understanding}, author = {Yang, Zeyuan and Chen, Delin and Yu, Xueyang and Shen, Maohao and Gan, Chuang}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {20168--20179}, doi = {10.1109/iccv51701.2025.01876} } @techreport{veo3_2025, title = {{Veo: a text-to-video generation system}}, author = {{Google DeepMind}}, year = {2025}, institution = {Google DeepMind}, type = {Technical report} } @inproceedings{li2025veu, title = {{VEU-Bench}: Towards Comprehensive Understanding of Video Editing}, author = {Li, Bozheng and Wu, Yongliang and Lu, Yi and Yu, Jiashuo and Tang, Licheng and Cao, Jiawang and Zhu, Wenqing and Sun, Yuyang and Wu, Jay and Zhu, Wenbo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {13671--13680}, doi = {10.1109/cvpr52734.2025.01276} } @inproceedings{vggsound2020, title = {VGGSound: A Large-Scale Audio-Visual Dataset}, author = {Chen, Honglie and Xie, Weidi and Vedaldi, Andrea and Zisserman, Andrew}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, year = {2020}, pages = {721--725}, doi = {10.1109/icassp40776.2020.9053174} } @inproceedings{yang2023vid2seq, title = {Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning}, author = {Yang, Antoine and Nagrani, Arsha and Seo, Paul Hongsuck and Miech, Antoine and Pont-Tuset, Jordi and Laptev, Ivan and Sivic, Josef and Schmid, Cordelia}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {10714--10726}, doi = {10.1109/cvpr52729.2023.01032} } @inproceedings{huang2025vid2world, title = {Vid2World: Crafting Video Diffusion Models to Interactive World Models}, author = {Huang, Siqiao and Wu, Jialong and Zhou, Qixing and Miao, Shangchen and Long, Mingsheng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{wanstreamer2026, title = {Video = World + Event Stream}, author = {Lianghua Huang and Zhi-Fan Wu and Yupeng Shi and Wei Wang and Mengyang Feng and Cheng Yu and Chen Liang and Junjie He and Chen-Wei Xie and Yu Liu and Jingren Zhou and Ang Wang and Bang Zhang and Baole Ai and Chongyang Zhong and Jinwei Qi and Kai Zhu and Pandeng Li and Peng Zhang and Wenyuan Zhang and Xinhua Cheng and Yitong Huang and Yun Zheng and Yuxiang Bao and Yuzheng Wang and Zhiwei Lin and Zoubin Bi}, year = {2026}, eprint = {2607.15038}, archiveprefix = {arXiv} } @inproceedings{ho2022video, title = {Video Diffusion Models}, author = {Ho, Jonathan and Salimans, Tim and Gritsenko, Alexey and Chan, William and Norouzi, Mohammad and Fleet, David}, booktitle = {Advances in Neural Information Processing Systems}, year = {2022}, volume = {35}, pages = {8633--8646} } @inproceedings{genception2026, title = {Video Generation Models Are General-Purpose Vision Learners}, author = {Wang, Letian and Zhang, Chuhan and Kabra, Rishabh and Uijlings, Jasper and Waslander, Steven and Zisserman, Andrew and Carreira, Joao and He, Kaiming and Andriluka, Misha and Bazavan, Eduard Gabriel and Zanfir, Andrei and Sminchisescu, Cristian}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {608--627}, doi = {10.1007/978-3-032-37369-4_33} } @misc{brooks2024video, title = {Video Generation Models As World Simulators}, author = {Brooks, Tim and Peebles, Bill and Holmes, Connor and DePue, Will and Guo, Yufei and Jing, Li and Schnurr, David and Taylor, Joe and Luhman, Troy and Luhman, Eric and Ng, Clarence and Wang, Ricky and Ramesh, Aditya}, year = {2024}, howpublished = {OpenAI publication} } @inproceedings{hu2025vpp, title = {Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations}, author = {Hu, Yucheng and Guo, Yanjiang and Wang, Pengchao and Chen, Xiaoyu and Wang, Yen-Jen and Zhang, Jianke and Sreenath, Koushil and Lu, Chaochao and Chen, Jianyu}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {24328--24346}, } @inproceedings{sridhar2025vreason, title = {Video Reasoning Without Training}, author = {Sridhar, Deepak and Bhardwaj, Kartikeya and Jeyaraj, Jeya Pradha and Vasconcelos, Nuno and Nayak, Ankita and Teague, Harris}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition -- Findings (CVPRF)}, year = {2026}, pages = {6253--6263}, doi = {10.1109/cvprf71909.2026.00600} } @inproceedings{liu2022videoswin, title = {Video Swin Transformer}, author = {Liu, Ze and Ning, Jia and Cao, Yue and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Hu, Han}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2022}, pages = {3202--3211}, doi = {10.1109/cvpr52688.2022.00320} } @article{tang2023videollmsurvey, title = {Video Understanding with Large Language Models: A Survey}, author = {Tang, Yunlong and Bi, Jing and Xu, Siting and Song, Luchuan and Liang, Susan and Wang, Teng and Zhang, Daoan and An, Jie and Lin, Jingyang and Zhu, Rongyi and Vosoughi, Ali and Huang, Chao and Zhang, Zeliang and Liu, Pinxin and Feng, Mingqian and Zheng, Feng and Zhang, Jianguo and Luo, Ping and Luo, Jiebo and Xu, Chenliang}, journal = {IEEE Transactions on Circuits and Systems for Video Technology}, year = {2026}, volume = {36}, number = {2}, pages = {1355--1376}, doi = {10.1109/tcsvt.2025.3566695} } @inproceedings{wu2025longtermspatialmemory, title = {Video World Models with Long-Term Spatial Memory}, author = {Wu, Tong and Yang, Shuai and Po, Ryan and Xu, Yinghao and Liu, Ziwei and Lin, Dahua and Wetzstein, Gordon}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {49371--49393}, doi = {10.52202/085713-1651} } @inproceedings{maaz-etal-2024-video, title = {Video-{C}hat{GPT}: Towards Detailed Video Understanding via Large Vision and Language Models}, author = {Maaz, Muhammad and Rasheed, Hanoona and Khan, Salman and Khan, Fahad}, booktitle = {Proceedings of the 62nd Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2024}, pages = {12585--12602}, doi = {10.18653/v1/2024.acl-long.679} } @inproceedings{videoholmes2025, title = {Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?}, author = {Cheng, Junhao and Ge, Yuying and Wang, Teng and Ge, Yixiao and Liao, Jing and Shan, Ying}, booktitle = {Computer Vision – ECCV 2026}, year = {2026}, pages = {539--556}, doi = {10.1007/978-3-032-37531-5_30} } @misc{song2026videoindex, title = {{Video-Index}: A Curated Meta-Benchmark for Video Understanding}, author = {Enxin Song and Yinuo Xu and Shusheng Yang and Wenhao Chai and Jiatao Gu}, year = {2026}, eprint = {2610.00960}, archiveprefix = {arXiv} } @inproceedings{jin2024videolavit, title = {Video-{L}a{VIT}: Unified Video-Language Pre-Training with Decoupled Visual-Motional Tokenization}, author = {Jin, Yang and Sun, Zhicheng and Xu, Kun and Xu, Kun and Chen, Liwei and Jiang, Hao and Huang, Quzhe and Song, Chengru and Liu, Yuliang and Zhang, Di and Song, Yang and Gai, Kun and Mu, Yadong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {22185--22209}, } @inproceedings{zhang-etal-2023-video, title = {Video-{LLaMA}: An Instruction-Tuned Audio-Visual Language Model for Video Understanding}, author = {Zhang, Hang and Li, Xin and Bing, Lidong}, booktitle = {Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations}, year = {2023}, pages = {543--553}, doi = {10.18653/v1/2023.emnlp-demo.49} } @inproceedings{lin2024videollava, title = {Video-{LLaVA}: Learning United Visual Representation by Alignment Before Projection}, author = {Lin, Bin and Ye, Yang and Zhu, Bin and Cui, Jiaxi and Ning, Munan and Jin, Peng and Yuan, Li}, booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing}, year = {2024}, pages = {5971--5984}, doi = {10.18653/v1/2024.emnlp-main.342} } @misc{kwan2026videommelogical, title = {Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning}, author = {Hohin Kwan and Hongyu Li and Ray Zhang and Manyuan Zhang and Xianghao Kong and Anyi Rao and Jiahao Xie and Si Liu}, year = {2026}, eprint = {2606.27828}, archiveprefix = {arXiv} } @misc{videommev2_2026, title = {Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding}, author = {Chaoyou Fu and Haozhi Yuan and Yuhao Dong and Yi-Fan Zhang and Yunhang Shen and Xiaoxing Hu and Xueying Li and Jinsen Su and Chengwu Long and Xiaoyao Xie and Yongkang Xie and Xiawu Zheng and Xue Yang and Haoyu Cao and Yunsheng Wu and Ziwei Liu and Xing Sun and Caifeng Shan and Ran He}, year = {2026}, eprint = {2604.05015}, archiveprefix = {arXiv} } @inproceedings{fu2025video, title = {Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-Modal LLMs in Video Analysis}, author = {Fu, Chaoyou and Dai, Yuhan and Luo, Yongdong and Li, Lei and Ren, Shuhuai and Zhang, Renrui and Wang, Zihan and Zhou, Chenyu and Shen, Yunhang and Zhang, Mengdan and Chen, Peixian and Li, Yanwei and Lin, Shaohui and Zhao, Sirui and Li, Ke and Xu, Tong and Zheng, Xiawu and Chen, Enhong and Shan, Caifeng and He, Ran and Sun, Xing}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {24108--24118}, doi = {10.1109/cvpr52734.2025.02245} } @inproceedings{hu2025video, title = {Video-{MMMU}: Evaluating Knowledge Acquisition from Multidisciplinary Professional Videos}, author = {Hu, Kairui and Wu, Penghao and Pu, Fanyi and Xiao, Wang and Yue, Xiang and Li, Bo and Zhang, Yuanhan and Liu, Ziwei}, booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)}, year = {2026}, pages = {27798--27828}, doi = {10.18653/v1/2026.acl-long.1281}, } @inproceedings{fei2024videoofthought, title = {{Video-of-Thought}: Step-by-Step Video Reasoning from Perception to Cognition}, author = {Fei, Hao and Wu, Shengqiong and Ji, Wei and Zhang, Hanwang and Zhang, Meishan and Lee, Mong-Li and Hsu, Wynne}, booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)}, year = {2024}, volume = {235}, pages = {13109--13125}, } @inproceedings{liu2023videop2p, title = {Video-P2P: Video Editing with Cross-Attention Control}, author = {Liu, Shaoteng and Zhang, Yuechen and Li, Wenbo and Lin, Zhe and Jia, Jiaya}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {8599--8608}, doi = {10.1109/cvpr52733.2024.00821} } @inproceedings{feng2025videor1, title = {Video-R1: Reinforcing Video Reasoning in MLLMs}, author = {Feng, Kaituo and Gong, Kaixiong and Li, Bohao and Guo, Zonghao and Wang, Yibing and Peng, Tianshuo and Wu, Junfei and Zhang, Xiaoying and Wang, Benyou and Yue, Xiangyu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {99114--99137}, doi = {10.52202/085713-3310} } @inproceedings{videoxl2024, title = {Video-XL: Extra-Long Vision Language Model for Hour-Scale Video Understanding}, author = {Shu, Yan and Liu, Zheng and Zhang, Peitian and Qin, Minghao and Zhou, Junjie and Liang, Zhengyang and Huang, Tiejun and Zhao, Bo}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {26160--26169}, doi = {10.1109/cvpr52734.2025.02436} } @inproceedings{wu2026video2lora, title = {Video2LoRA: Unified Semantic-Controlled Video Generation via Per-Reference-Video LoRA}, author = {Wu, Zexi and Li, Baolu and Dai, Jing and Zhang, Yiming and Ma, Yue and Wang, Qinghe and Jia, Xu and Xu, Hongming}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition -- Findings (CVPRF)}, year = {2026}, pages = {4202--4212}, doi = {10.1109/cvprf71909.2026.00406} } @misc{zhi2025videoagent2, title = {VideoAgent2: Enhancing the LLM-Based Agent System for Long-Form Video Understanding by Uncertainty-Aware CoT}, author = {Zhuo Zhi and Qiangqiang Wu and Minghe shen and Wenbo Li and Yinchuan Li and Kun Shao and Kaiwen Zhou}, year = {2025}, eprint = {2504.04471}, archiveprefix = {arXiv} } @inproceedings{fan2024videoagentmemory, title = {VideoAgent: A Memory-Augmented Multimodal Agent for Video Understanding}, author = {Yue Fan and Xiaojian Ma and Rujie Wu and yuntao du and Jiaqi Li and Zhi Gao and Qing Li}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, doi = {10.1007/978-3-031-72670-5_5} } @misc{zhou2026videoagentediting, title = {VideoAgent: All-in-One Framework for Video Understanding and Editing}, author = {Hengji Zhou and Lingxuan Huang and Jian Wang and Bing Zhou and Si Wu and Lianghao Xia and Chao Huang}, year = {2026}, eprint = {2606.23327}, archiveprefix = {arXiv} } @inproceedings{wang2024videoagentlong, title = {VideoAgent: Long-Form Video Understanding with Large Language Model As Agent}, author = {Xiaohan Wang and Yuhui Zhang and Orr Zohar and Serena Yeung-Levy}, booktitle = {Computer Vision -- ECCV 2024}, year = {2024}, doi = {10.1007/978-3-031-72989-8_4} } @misc{soni2024videoagent, title = {VideoAgent: Self-Improving Video Generation}, author = {Achint Soni and Sreyas Venkataraman and Abhranil Chandra and Sebastian Fischmeister and Percy Liang and Bo Dai and Sherry Yang}, year = {2024}, eprint = {2410.10076}, archiveprefix = {arXiv} } @inproceedings{sun2019videobert, title = {VideoBERT: A Joint Model for Video and Language Representation Learning}, author = {Sun, Chen and Myers, Austin and Vondrick, Carl and Murphy, Kevin and Schmid, Cordelia}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2019}, pages = {7464--7473}, doi = {10.1109/iccv.2019.00756} } @inproceedings{wang2025videochata1, title = {VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning}, author = {Wang, Zikang and Chen, Boyu and Yue, Zhengrong and Wang, Yi and Qiao, Yu and Wang, Limin and Wang, Yali}, booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence}, year = {2026}, volume = {40}, number = {13}, pages = {10467--10475}, doi = {10.1609/aaai.v40i13.38018} } @inproceedings{li2025videochatflash, title = {VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling}, author = {Li, Xinhao and Wang, Yi and Yu, Jiashuo and Zeng, Xiangyu and Zhu, Yuhan and Huang, Haian and Gao, Jianfei and Li, Kunchang and He, Yinan and Wang, Chenting and Qiao, Yu and Wang, Yali and Wang, Limin}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{li2025videochatr1, title = {VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning}, author = {Xinhao Li and Ziang Yan and Desen Meng and Lu Dong and Xiangyu Zeng and Yinan He and Yali Wang and Yu Qiao and Yi Wang and Limin Wang}, year = {2025}, eprint = {2504.06958}, archiveprefix = {arXiv} } @misc{videochat3_2026, title = {VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding}, author = {Xinhao Li and Yuhan Zhu and Xiangyu Zeng and Yuhao Dong and Haoning Wu and Zhiqiu Zhang and Yuandong Yang and Changlian Ma and Qingyu Zhang and Yansong Shi and Xinyu Chen and Haoran Chen and Zizheng Huang and Jun Zhang and Kun Ouyang and Lin Sui and Ziang Yan and Yicheng Xu and Chenting Wang and Yinan He and Hongjie Zhang and Yi Wang and Yu Qiao and Yali Wang and Ziwei Liu and Kai Chen and Limin Wang}, year = {2026}, eprint = {2607.14935}, archiveprefix = {arXiv} } @article{videochat2023, title = {VideoChat: Chat-Centric Video Understanding}, author = {Li, Kunchang and He, Yinan and Wang, Yi and Li, Yizhuo and Wang, Wenhai and Luo, Ping and Wang, Yali and Wang, Limin and Qiao, Yu}, journal = {Science China Information Sciences}, year = {2025}, volume = {68}, number = {10}, doi = {10.1007/s11432-024-4321-9} } @inproceedings{xu2021videoclip, title = {VideoCLIP: Contrastive Pre-Training for Zero-Shot Video-Text Understanding}, author = {Xu, Hu and Ghosh, Gargi and Huang, Po-Yao and Okhonko, Dmytro and Aghajanyan, Armen and Metze, Florian and Zettlemoyer, Luke and Feichtenhofer, Christoph}, booktitle = {Conference on Empirical Methods in Natural Language Processing (EMNLP)}, year = {2021}, pages = {6787--6800}, doi = {10.18653/v1/2021.emnlp-main.544} } @misc{Yan2023VideoCoCa, title = {VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners}, author = {Yan, Shen and Zhu, Tao and Wang, Zirui and Cao, Yuan and Zhang, Mi and Ghosh, Soham and Wu, Yonghui and Yu, Jiahui}, year = {2022}, eprint = {2212.04979}, archiveprefix = {arXiv} } @inproceedings{wang2023videocomposer, title = {{VideoComposer}: Compositional Video Synthesis with Motion Controllability}, author = {Wang, Xiang and Yuan, Hangjie and Zhang, Shiwei and Chen, Dayou and Wang, Jiuniu and Zhang, Yingya and Shen, Yujun and Zhao, Deli and Zhou, Jingren}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {7594--7611}, doi = {10.52202/075280-0334} } @misc{hu2023videocontrolnet, title = {VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet}, author = {Zhihao Hu and Dong Xu}, year = {2023}, eprint = {2307.14073}, archiveprefix = {arXiv} } @inproceedings{chen2024videocrafter2, title = {VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models}, author = {Chen, Haoxin and Zhang, Yong and Cun, Xiaodong and Xia, Menghan and Wang, Xintao and Weng, Chao and Shan, Ying}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {7310--7320}, doi = {10.1109/cvpr52733.2024.00698} } @inproceedings{lin2024videodirectorgpt, title = {VideoDirector{GPT}: Consistent Multi-Scene Video Generation via {LLM}-Guided Planning}, author = {Han Lin and Abhay Zala and Jaemin Cho and Mohit Bansal}, booktitle = {First Conference on Language Modeling}, year = {2024} } @misc{yuan2025videoexplorer, title = {VideoExplorer: Think with Videos for Agentic Long-Video Understanding}, author = {Huaying Yuan and Zheng Liu and Junjie Zhou and Hongjin Qian and Yan Shu and Nicu Sebe and Ji-Rong Wen and Zhicheng Dou}, year = {2025}, eprint = {2506.10821}, archiveprefix = {arXiv} } @inproceedings{atanov2026videoflextok, title = {{V}ideo{F}lex{T}ok: Flexible-Length Coarse-to-Fine Video Tokenization}, author = {Atanov, Andrei and Allardice, Jesse and Bachmann, Roman and Kar, O\u{g}uzhan Fatih and Hjelm, R Devon and Griffiths, David and Fu, Peter and Dehghan, Afshin and Zamir, Amir}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {4259--4282}, } @misc{zhang2026videogaia, title = {{VideoGAIA}: A Benchmark for General {AI} Assistants on Agentic Video Understanding}, author = {Fan Zhang and Guangming Yao and Jinyang Wu and Hao Wu and Zheng Lian and Xinyu Geng and Jingdong Chen and Yi Yuan and Pheng-Ann Heng}, year = {2026}, eprint = {2608.14718}, archiveprefix = {arXiv} } @misc{yan2021videogpt, title = {{VideoGPT}: Video Generation Using {VQ-VAE} and Transformers}, author = {Yan, Wilson and Zhang, Yunzhi and Abbeel, Pieter and Srinivas, Aravind}, year = {2021}, eprint = {2104.10157}, archiveprefix = {arXiv} } @misc{wang2024videohallucer, title = {VideoHallucer: Evaluating Intrinsic and Extrinsic Hallucinations in Large Video-Language Models}, author = {Yuxuan Wang and Yueqian Wang and Dongyan Zhao and Cihang Xie and Zilong Zheng}, year = {2024}, eprint = {2406.16338}, archiveprefix = {arXiv} } @misc{cheng2024videollama2, title = {VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs}, author = {Zesen Cheng and Sicong Leng and Hang Zhang and Yifei Xin and Xin Li and Guanzheng Chen and Yongxin Zhu and Wenqi Zhang and Ziyang Luo and Deli Zhao and Lidong Bing}, year = {2024}, eprint = {2406.07476}, archiveprefix = {arXiv} } @misc{videollama3_2025, title = {VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding}, author = {Boqiang Zhang and Kehan Li and Zesen Cheng and Zhiqiang Hu and Yuqian Yuan and Guanzheng Chen and Sicong Leng and Yuming Jiang and Hang Zhang and Xin Li and Peng Jin and Wenqi Zhang and Fan Wang and Lidong Bing and Deli Zhao}, year = {2025}, eprint = {2501.13106}, archiveprefix = {arXiv} } @inproceedings{chen2024videollmonline, title = {VideoLLM-Online: Online Video Large Language Model for Streaming Video}, author = {Chen, Joya and Lv, Zhaoyang and Wu, Shiwei and Lin, Kevin Qinghong and Song, Chenan and Gao, Difei and Liu, Jia-Wei and Gao, Ziteng and Mao, Dongxing and Shou, Mike Zheng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2024}, pages = {18407--18418}, doi = {10.1109/cvpr52733.2024.01742} } @inproceedings{zuo2025videolucy, title = {VideoLucy: Deep Memory Backtracking for Long Video Understanding}, author = {Zuo, Jialong and Deng, Yongtai and Kong, Lingdong and Yang, Jingkang and Jin, Rui and Zhang, Yiwei and Sang, Nong and Pan, Liang and Liu, Ziwei and Gao, Changxin}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {25660--25691}, doi = {10.52202/085713-0864} } @inproceedings{wang2023videomae, title = {VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking}, author = {Wang, Limin and Huang, Bingkun and Zhao, Zhiyu and Tong, Zhan and He, Yinan and Wang, Yi and Wang, Yali and Qiao, Yu}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {14549--14560}, doi = {10.1109/cvpr52729.2023.01398} } @inproceedings{tong2022videomae, title = {VideoMAE: Masked Autoencoders Are Data-Efficient Learners for Self-Supervised Video Pre-Training}, author = {Tong, Zhan and Song, Yibing and Wang, Jue and Wang, Limin}, booktitle = {Advances in Neural Information Processing Systems}, year = {2022}, volume = {35}, pages = {10078--10093}, doi = {10.52202/068431-0732} } @inproceedings{yu2025videomar, title = {VideoMAR: Autoregressive Video Generation with Continuous Tokens}, author = {Yu, Hu and Gong, Biao and Yuan, Hangjie and Zheng, DanDan and Chai, Weilong and Chen, Jingdong and Zheng, Kecheng and Zhao, Feng}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {56928--56958}, doi = {10.52202/085713-1907} } @inproceedings{liu2025videomind, title = {VideoMind: A Chain-of-LoRA Agent for Temporal-Grounded Video Reasoning}, author = {Liu, Ye and Lin, Kevin Qinghong and Chen, Chang Wen and Shou, Mike Zheng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{kugo2025videomultiagents, title = {VideoMultiAgents: A Multi-Agent Framework for Video Question Answering}, author = {Noriyuki Kugo and Xiang Li and Zixin Li and Ashish Gupta and Arpandeep Khatua and Nidhish Jain and Chaitanya Patel and Yuta Kyuragi and Yasunori Ishii and Masamoto Tanabiki and Kazuki Kozuka and Ehsan Adeli}, year = {2025}, eprint = {2504.20091}, archiveprefix = {arXiv} } @misc{videoodyssey2026, title = {VideoOdyssey: A Benchmark for Ultra-Long-Context and Omni-Modal Video Understanding}, author = {Haichen He and Jiayi Zhou and Sifeng Shang and Yihan Hu and Yuanhan Zhang and Kaiyang Zhou}, year = {2026}, eprint = {2605.22907}, archiveprefix = {arXiv} } @inproceedings{jiang2025videop2r, title = {VideoP2R: Video Understanding from Perception to Reasoning}, author = {Jiang, Yifan and Wang, Yueying and Zhao, Rui and Parag, Toufiq and Chen, Zhimin and Liao, Zhenyu and Unnikrishnan, Jayakrishnan}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition -- Findings (CVPRF)}, year = {2026}, pages = {8304--8314}, doi = {10.1109/cvprf71909.2026.00797} } @inproceedings{bansal2025videophy2, title = {VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation}, author = {Bansal, Hritik and Peng, Clark and Bitton, Yonatan and Goldenberg, Roman and Grover, Aditya and Chang, Kai-Wei}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{bansal2024videophy, title = {VideoPhy: Evaluating Physical Commonsense for Video Generation}, author = {Bansal, Hritik and Lin, Zongyu and Xie, Tianyi and Zong, Zeshun and Yarom, Michal and Bitton, Yonatan and Jiang, Chenfanfu and Sun, Yizhou and Chang, Kai-Wei and Grover, Aditya}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{kondratyuk2024videopoet, title = {VideoPoet: A Large Language Model for Zero-Shot Video Generation}, author = {Kondratyuk, Dan and Yu, Lijun and Gu, Xiuye and Lezama, Jose and Huang, Jonathan and Schindler, Grant and Hornung, Rachel and Birodkar, Vighnesh and Yan, Jimmy and Chiu, Ming-Chang and Somandepalli, Krishna and Akbari, Hassan and Alon, Yair and Cheng, Yong and Dillon, Joshua V. and Gupta, Agrim and Hahn, Meera and Hauth, Anja and Hendon, David and Martinez, Alonso and Minnen, David and Sirotenko, Mikhail and Sohn, Kihyuk and Yang, Xuan and Adam, Hartwig and Yang, Ming-Hsuan and Essa, Irfan and Wang, Huisheng and Ross, David A and Seybold, Bryan and Jiang, Lu}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {25105--25124}, } @inproceedings{zhao2024videoprism, title = {{V}ideo{P}rism: A Foundational Visual Encoder for Video Understanding}, author = {Zhao, Long and Gundavarapu, Nitesh Bharadwaj and Yuan, Liangzhe and Zhou, Hao and Yan, Shen and Sun, Jennifer J. and Friedman, Luke and Qian, Rui and Weyand, Tobias and Zhao, Yue and Hornung, Rachel and Schroff, Florian and Yang, Ming-Hsuan and Ross, David A and Wang, Huisheng and Adam, Hartwig and Sirotenko, Mikhail and Liu, Ting and Gong, Boqing}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, year = {2024}, volume = {235}, pages = {60785--60811}, } @inproceedings{jeong2025videoragcorpus, title = {VideoRAG: Retrieval-Augmented Generation Over Video Corpus}, author = {Jeong, Soyeong and Kim, Kangsan and Baek, Jinheon and Hwang, Sung Ju}, booktitle = {Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2025}, year = {2025}, pages = {21278--21298}, doi = {10.18653/v1/2025.findings-acl.1096} } @inproceedings{ren2025videoragextreme, title = {VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos}, author = {Ren, Xubin and Xu, Lingrui and Xia, Long and Wang, Shuaiqiang and Yin, Dawei and Huang, Chao}, booktitle = {Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1}, year = {2026}, pages = {2390--2401}, doi = {10.1145/3770854.3783944} } @inproceedings{zhang2025videorepa, title = {VideoREPA: Learning Physics for Video Generation Through Relational Alignment with Foundation Models}, author = {Zhang, Xiangdong and Liao, Jiaqi and Zhang, Shaofeng and Meng, Fanqing and Wan, Xiangpeng and Yan, Junchi and Cheng, Yu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {122647--122676}, doi = {10.52202/085713-4091} } @article{he2025videoscore2, title = {VideoScore2: Think Before You Score in Generated Video Evaluation}, author = {Xuan He and Dongfu Jiang and Ping Nie and Minghao Liu and Zhengxuan Jiang and Mingyi Su and Wentao Ma and Junru Lin and Chun Ye and Yi Lu and Keming Wu and Benjamin Schneider and Quy Duc Do and Zhuofeng Li and Yiming Jia and Yuxuan Zhang and Guo Cheng and Haozhe Wang and Wangchunshu Zhou and Qunshu Lin and Yuanxing Zhang and Ge Zhang and Wenhao Huang and Wenhu Chen}, journal = {Transactions on Machine Learning Research}, year = {2026}, issn = {2835-8856} } @inproceedings{he2024videoscore, title = {{V}ideo{S}core: Building Automatic Metrics to Simulate Fine-Grained Human Feedback for Video Generation}, author = {He, Xuan and Jiang, Dongfu and Zhang, Ge and Ku, Max and Soni, Achint and Siu, Sherman and Chen, Haonan and Chandra, Abhranil and Jiang, Ziyan and Arulraj, Aaran and Wang, Kai and Do, Quy Duc and Ni, Yuansheng and Lyu, Bohan and Narsupalli, Yaswanth and Fan, Rongqi and Lyu, Zhiheng and Lin, Bill Yuchen and Chen, Wenhu}, booktitle = {Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing}, year = {2024}, pages = {2105--2123}, doi = {10.18653/v1/2024.emnlp-main.127} } @inproceedings{li2026videothinker, title = {VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning}, author = {Li, Chenglin and Chen, Qianglong and Han, Feng and Wang, Yikun and Yin, Xingxi and Gong, Yan and Li, Ruilin and Zhang, Yin and Wang, Jiaqi}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition -- Findings (CVPRF)}, year = {2026}, pages = {8229--8237}, doi = {10.1109/cvprf71909.2026.00790} } @inproceedings{wang2024videotree, title = {VideoTree: Adaptive Tree-Based Video Representation for LLM Reasoning on Long Videos}, author = {Wang, Ziyang and Yu, Shoubin and Stengel-Eskin, Elias and Yoon, Jaehong and Cheng, Feng and Bertasius, Gedas and Bansal, Mohit}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {3272--3283}, doi = {10.1109/cvpr52734.2025.00311} } @misc{vidus1_2026, title = {Vidu S1: A Real-Time Interactive Video Generation Model}, author = {Jintao Zhang and Kai Jiang and Jintao Chen and Xu Wang and Yang Luo and Yuji Wang and Dechuang Chen and Jungang Li and Chengyang Ye and Marco Chen and Hongzhou Zhu and Min Zhao and Yuxuan Jiang and Zhengkun Huang and Chendong Xiang and Kaiwen Zheng and Haoxu Wang and Xiaohang Wang and Qi Jia and Xin Chen and Yimin Chen and Youhe Jiang and Fangcheng Fu and Zhijie Deng and Fan Bao and Jianfei Chen and Jun Zhu}, year = {2026}, eprint = {2607.03118}, archiveprefix = {arXiv} } @misc{vidus2_2026, title = {{Vidu S2}: Real-Time Interactive, Editable, and Spatial Video Generation}, author = {Jintao Zhang and Kai Jiang and Jintao Chen and Xu Wang and Deyuan Liu and Jungang Li and Dechuang Chen and Ming Lin and Jingjiang Zhou and Haopeng Jin and Qi Jia and Xiaohang Wang and Yaole Wang and Zhanqiang Zhang and Ran Li and Zhengkun Huang and Shuyue Xiong and Yuji Wang and Zikun Dai and Hui He and Yang Luo and Mang Ning and Weiqi Feng and Chengyang Ye and Xinyue Lin and Min Zhao and Hongzhou Zhu and Hengkai Tan and Zeyuan Wang and Chendong Xiang and Kaiwen Zheng and Zhijie Deng and Fan Bao and Jianfei Chen and Jun Zhu}, year = {2026}, eprint = {2609.11638}, archiveprefix = {arXiv} } @inproceedings{wu2025vilauunifiedfoundationmodel, title = {VILA-U: A Unified Foundation Model Integrating Visual Understanding and Generation}, author = {Wu, Yecheng and Zhang, Zhuoyang and Chen, Junyu and Tang, Haotian and Li, Dacheng and Fang, Yunhao and Zhu, Ligeng and Xie, Enze and Yin, Hongxu and Yi, Li and Han, Song and Lu, Yao}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2025} } @inproceedings{suris2023vipergpt, title = {ViperGPT: Visual Inference via Python Execution for Reasoning}, author = {Sur{\'\i}s, D{\'\i}dac and Menon, Sachit and Vondrick, Carl}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2023}, pages = {11888--11898}, } @book{marr1982vision, author={Marr, David}, title={Vision: A Computational Investigation into the Human Representation and Processing of Visual Information}, year={1982} } @misc{liang2026visphyworld, title = {VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction}, author = {Jiarong Liang and Max Ku and Ka-Hei Hui and Ping Nie and Wenhu Chen}, year = {2026}, eprint = {2602.13294}, archiveprefix = {arXiv} } @inproceedings{gao2024vista, title = {Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability}, author = {Gao, Shenyuan and Yang, Jiazhi and Chen, Li and Chitta, Kashyap and Qiu, Yihang and Geiger, Andreas and Zhang, Jun and Li, Hongyang}, booktitle = {Advances in Neural Information Processing Systems}, year = {2024}, volume = {37}, pages = {91560--91596}, doi = {10.52202/079017-2906} } @inproceedings{long2025vista, title = {VISTA: A Test-Time Self-Improving Video Generation Agent}, author = {Long, Do Xuan and Wan, Xingchen and Nakhost, Hootan and Lee, Chen-Yu and Pfister, Tomas and Arik, Sercan \"O.}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {6021--6032}, } @inproceedings{huang2025vistadpo, title = {{VistaDPO}: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models}, author = {Huang, Haojian and Chen, Haodong and Wu, Shengqiong and Luo, Meng and Fu, Jinlan and Du, Xinya and Zhang, Hanwang and Fei, Hao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {25185--25203}, } @inproceedings{liu2023visual, title = {Visual Instruction Tuning}, author = {Liu, Haotian and Li, Chunyuan and Wu, Qingyang and Lee, Yong Jae}, booktitle = {Advances in Neural Information Processing Systems}, year = {2023}, volume = {36}, pages = {34892--34916}, doi = {10.52202/075280-1516} } @inproceedings{gupta2022visprog, title = {Visual Programming: Compositional Visual Reasoning Without Training}, author = {Gupta, Tanmay and Kembhavi, Aniruddha}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2023}, pages = {14953--14962}, doi = {10.1109/cvpr52729.2023.01436} } @inproceedings{arnab2021vivit, title = {ViViT: A Video Vision Transformer}, author = {Arnab, Anurag and Dehghani, Mostafa and Heigold, Georg and Sun, Chen and Lu\v{c}i\'c, Mario and Schmid, Cordelia}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2021}, pages = {6836--6846}, doi = {10.1109/iccv48922.2021.00676} } @inproceedings{yang2025vlipp, title = {{VLIPP}: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior}, author = {Yang, Xindi and Li, Baolu and Zhang, Yiming and Yin, Zhenfei and Bai, Lei and Ma, Liqian and Wang, Zhiyong and Cai, Jianfei and Wong, Tien-Tsin and Lu, Huchuan and Jia, Xu}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {12360--12370}, doi = {10.1109/iccv51701.2025.01149} } @inproceedings{corona2025vlogger, title = {{VLOGGER}: Multimodal Diffusion for Embodied Avatar Synthesis}, author = {Corona, Enric and Zanfir, Andrei and Bazavan, Eduard Gabriel and Kolotouros, Nikos and Alldieck, Thiemo and Sminchisescu, Cristian}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2025}, pages = {15896--15908}, doi = {10.1109/cvpr52734.2025.01482} } @inproceedings{ling2025vmbench, title = {{VMBench}: A Benchmark for Perception-Aligned Video Motion Generation}, author = {Ling, Xinran and Zhu, Chen and Wu, Meiqi and Li, Hangyu and Feng, Xiaokun and Yang, Cundian and Hao, Aiming and Zhu, Jiashu and Wu, Jiahong and Chu, Xiangxiang}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {13087--13098}, doi = {10.1109/iccv51701.2025.01216} } @inproceedings{li2025vmem, title = {{VMem}: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory}, author = {Li, Runjia and Torr, Philip and Vedaldi, Andrea and Jakab, Tomas}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {25690--25699}, doi = {10.1109/iccv51701.2025.02383} } @inproceedings{chu2025wanmove, title = {Wan-Move: Motion-Controllable Video Generation via Latent Trajectory Guidance}, author = {Chu, Ruihang and He, Yefei and Chen, Zhekai and Zhang, Shiwei and Xu, Xiaogang and xia, bin and WANG, Dingdong and Yi, Hongwei and Liu, Xihui and Zhao, Hengshuang and Liu, Yu and Zhang, Yingya and Yang, Yujiu}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {404--432}, doi = {10.52202/085713-0014} } @misc{wan2025open, title = {Wan: Open and Advanced Large-Scale Video Generative Models}, author = {Team Wan and Ang Wang and Baole Ai and Bin Wen and Chaojie Mao and Chen-Wei Xie and Di Chen and Feiwu Yu and Haiming Zhao and Jianxiao Yang and Jianyuan Zeng and Jiayu Wang and Jingfeng Zhang and Jingren Zhou and Jinkai Wang and Jixuan Chen and Kai Zhu and Kang Zhao and Keyu Yan and Lianghua Huang and Mengyang Feng and Ningyi Zhang and Pandeng Li and Pingyu Wu and Ruihang Chu and Ruili Feng and Shiwei Zhang and Siyang Sun and Tao Fang and Tianxing Wang and Tianyi Gui and Tingyu Weng and Tong Shen and Wei Lin and Wei Wang and Wei Wang and Wenmeng Zhou and Wente Wang and Wenting Shen and Wenyuan Yu and Xianzhong Shi and Xiaoming Huang and Xin Xu and Yan Kou and Yangyu Lv and Yifei Li and Yijing Liu and Yiming Wang and Yingya Zhang and Yitong Huang and Yong Li and You Wu and Yu Liu and Yulin Pan and Yun Zheng and Yuntao Hong and Yupeng Shi and Yutong Feng and Zeyinzi Jiang and Zhen Han and Zhi-Fan Wu and Ziyu Liu}, year = {2025}, eprint = {2503.20314}, archiveprefix = {arXiv} } @misc{rajpal2026waypoint15, title = {Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware}, author = {Rajit Rajpal and Shahbuland Matiana and Liew Wei Pyn and Anmol Agarwal and Ryan Craig and Andrew Lapp and Mithun Hunsur and Sami BuGhanem and Scottie Fox and Aaron Sanders and Carson Poole and Irene Park and Dave Rossi and Spencer Frazier and Louis Castricato}, year = {2026}, eprint = {2609.37107}, archiveprefix = {arXiv} } @misc{ying2026wbench, title = {WBench: A Comprehensive Multi-Turn Benchmark for Interactive Video World Model Evaluation}, author = {Kaining Ying and Hengrui Hu and Siyu Ren and Jiamu Li and Fengjiao Chen and Ziwen Wang and Xuezhi Cao and Xunliang Cai and Henghui Ding}, year = {2026}, eprint = {2605.25874}, archiveprefix = {arXiv} } @misc{tan2026pokeworld, title = {What Can Latent World Models Know? Physical Information in Multimodal Predictive Representations}, author = {Tan, Kaizhen and Xu, Sizhe and Xu, Xin and Tao, Siru and Li, Yixiao and Hong, Hanzhe and Feng, Yang and Du, Heqing and Wang, Zhaonan}, year = {2026}, eprint = {2607.27017}, archiveprefix = {arXiv} } @article{terver2025jepawmstudy, title = {What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?}, author = {Basile Terver and Tsung-Yen Yang and Jean Ponce and Adrien Bardes and Yann LeCun}, journal = {Transactions on Machine Learning Research}, year = {2026}, issn = {2835-8856}, } @misc{whatifworld2026, title = {What-If World: A Causal Benchmark for General World Models in Embodied Scenarios}, author = {Kunlin Cai and Rui Song and Jinghuai Zhang and Kaiyuan Zhang and Pranav Bodapati and Alicia Yu and Fnu Suya and Mohammad Rostami and Jiaqi Ma and Yuan Tian}, year = {2026}, eprint = {2605.27589}, archiveprefix = {arXiv} } @inproceedings{vidstg2020, title = {Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences}, author = {Zhang, Zhu and Zhao, Zhou and Zhao, Yang and Wang, Qi and Liu, Huasheng and Gao, Lianli}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2020}, pages = {10665--10674}, doi = {10.1109/cvpr42600.2020.01068} } @misc{liu2026worldembedding, title = {World Embedding Benchmark}, author = {Yiqi Liu and Ruifeng Yuan and Yang Wang and Long Li and Fengyu Cai and Hou Pong Chan and Jialin Yu and Hao Zhang and Chenghua Lin and Chenghao Xiao}, year = {2026}, eprint = {2610.03632}, archiveprefix = {arXiv} } @misc{mei2025c3, title = {World Models That Know When They Don't Know -- Controllable Video Generation with Calibrated Uncertainty}, author = {Mei, Zhiting and Yin, Tenny and Baker, Micah and Shorinwa, Ola and Majumdar, Anirudha}, year = {2025}, eprint = {2512.05927}, archiveprefix = {arXiv} } @inproceedings{zhang2025worldinworld, title = {World-in-World: World Models in a Closed-Loop World}, author = {Zhang, Jiahan and Jiang, Muqing and Dai, Nanru and Lu, Taiming and Uzunoglu, Arda and Zhang, Shunchi and Wei, Yana and Wang, Jiahao and Patel, Vishal M. and Liang, Paul Pu and Khashabi, Daniel and Peng, Cheng and Chellappa, Rama and Shu, Tianmin and Yuille, Alan and Du, Yilun and Chen, Jieneng}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @misc{yang2026wla0, title = {World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis}, author = {Yi Yang and Zhihong Liu and Siqi Kou and Yiyang Chen and Yanzhe Hu and Jianbo Zhou and Boyuan Zhao and Zhijie Wei and Xiao Xia and Xueqi Li and Pengfei Liu and Zhijie Deng}, year = {2026}, eprint = {2606.05979}, archiveprefix = {arXiv} } @inproceedings{worldr1_2026, title = {World-R1: Reinforcing 3{D} Constraints for Text-to-Video Generation}, author = {Wang, Weijie and He, Xiaoxuan and Gu, Youping and Yang, Yifan and Zhang, Zeyu and He, Yefei and Ding, Yanbo and Hu, Xirui and Chen, Donny Y. and He, Zhiyuan and Yang, Yuqing and Zhuang, Bohan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {126569--126597}, } @misc{liu2026worldvlaloop, title = {World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy}, author = {Xiaokang Liu and Zechen Bai and Hai Ci and Kevin Yuchen Ma and Mike Zheng Shou}, year = {2026}, eprint = {2602.06508}, archiveprefix = {arXiv} } @article{shang2026worldarena, title = {WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models}, author = {Shang, Yu and Li, Zhuohang and Ma, Yiding and Su, Weikang and Jin, Xin and Wang, Ziyou and Jin, Lei and Zhang, Xin and Tang, Yinzhou and Su, Haisheng and Gao, Chen and Wu, Wei and Liu, Xihui and Shah, Dhruv and Zhang, Zhaoxiang and Chen, Zhibo and Zhu, Jun and Tian, Yonghong and Chua, Tat-Seng and Wang, Xin and Zhu, Wenwu and Li, Yong}, journal = {AI Open}, year = {2026}, volume = {7}, pages = {208--226}, doi = {10.1016/j.aiopen.2026.07.002} } @misc{worldbench2026, title = {WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts}, author = {Rishi Upadhyay and Howard Zhang and Jim Solomon and Ayush Agrawal and Yunhao Ba and Alex Wong and Celso M de Melo and Achuta Kadambi}, year = {2026}, eprint = {2601.21282}, archiveprefix = {arXiv} } @inproceedings{feng2026worldcache, title = {{W}orld{C}ache: Accelerating World Models for Free via Heterogeneous Token Caching}, author = {Feng, Weilun and Fan, Guoxin and Qin, Haotong and Wu, Mingqiang and Li, Yuqi and Li, Xiangqi and An, Zhulin and Huang, Libo and Wang, Dingrui and Liao, Longlong and Magno, Michele and Xu, Yongjun and Yang, Chuanguang}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, year = {2026}, volume = {306}, pages = {30040--30065}, } @misc{wang2026worlddirector, title = {WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory}, author = {Hanlin Wang and Hao Ouyang and Qiuyu Wang and Wen Wang and Qingyan Bai and Ka Leong Cheng and Yue Yu and Yixuan Li and Yihao Meng and Zichen Liu and Yanhong Zeng and Yujun Shen and Qifeng Chen}, year = {2026}, eprint = {2607.02517}, archiveprefix = {arXiv} } @misc{li2025worldeval, title = {WorldEval: World Model As Real-World Robot Policies Evaluator}, author = {Yaxuan Li and Yichen Zhu and Junjie Wen and Chaomin Shen and Yi Xu}, year = {2025}, eprint = {2505.19017}, archiveprefix = {arXiv} } @inproceedings{quevedo2025worldgym, title = {WorldGym: World Model As an Environment for Policy Evaluation}, author = {Quevedo, Julian and Sharma, Ansh Kumar and Sun, Yixiang and Suryavanshi, Varad and Liang, Percy and Yang, Sherry}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2026} } @inproceedings{liang2025worldlens, title = {WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World}, author = {Liang, Ao and Kong, Lingdong and Yan, Tianyi and Liu, Hongsi and Yang, Yu and Huang, Ziqi and Yin, Wei and Zuo, Jialong and Hu, Yixuan and Zhu, Dekai and Lu, Dongyue and Liu, Youquan and Jiang, Guangfeng and Li, Linfeng and Li, Xiangtai and Zhuo, Long and Ng, Lai Xing and Cottereau, Benoit R. and Gao, Changxin and Pan, Liang and Ooi, Wei Tsang and Liu, Ziwei}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {36385--36399}, } @misc{xu2026worldmark, title = {WorldMark: A Unified Benchmark Suite for Interactive Video World Models}, author = {Xiaojie Xu and Zhengyuan Lin and Kang He and Yukang Feng and Xiaofeng Mao and Yuanyang Yin and Yongtao Ge and Kaipeng Zhang}, year = {2026}, eprint = {2604.21686}, archiveprefix = {arXiv} } @inproceedings{xiao2025worldmem, title = {WorldMem: Long-Term Consistent World Simulation with Memory}, author = {Xiao, Zeqi and LAN, Yushi and Zhou, Yifan and Ouyang, Wenqi and Yang, Shuai and Zeng, Yanhong and Pan, Xingang}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {49632--49652}, doi = {10.52202/085713-1659} } @inproceedings{yeo2025worldmm, title = {WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning}, author = {Yeo, Woongyeong and Kim, Kangsan and Yoon, Jaehong and Hwang, Sung Ju}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {25599--25609}, } @inproceedings{li2025worldmodelbench, title = {WorldModelBench: Judging Video Generation Models As World Models}, author = {Li, Dacheng and Fang, Yunhao and Chen, Yukang and Yang, Shuo and Cao, Shiyi and Wong, Justin and Luo, Michael and Wang, Xiaolong and Yin, Hongxu and Gonzalez, Joseph E. and Stoica, Ion and Han, Song and Lu, Yao}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, doi = {10.52202/085713-1834} } @misc{worldolympiad2026, title = {WorldOlympiad: Can Your World Model Survive a Triathlon?}, author = {Yuke Zhao and Wangbo Zhao and Weijie Wang and Zeyu Zhang and Dakai An and Akide Liu and Yinghao Yu and Jiasheng Tang and Fan Wang and Wei Wang and Bohan Zhuang}, year = {2026}, eprint = {2606.11129}, archiveprefix = {arXiv} } @misc{chen2025worldprediction, title = {WorldPrediction: A Benchmark for High-Level World Modeling and Long-Horizon Procedural Planning}, author = {Delong Chen and Willy Chung and Yejin Bang and Ziwei Ji and Pascale Fung}, year = {2025}, eprint = {2506.04363}, archiveprefix = {arXiv} } @misc{worldroambench2026, title = {WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models}, author = {Ting-Bing Xu and Jiacheng Sui and Zhe Gao and Kewei Shi and Wenjin Yang and Zhicheng Liu and Zhaoxu Sun and Mingchao Sun and Hongyu Pan and Fan Jiang and Mu Xu and Qi Fan and Yang Gao and Yong Li and Baoquan Chen}, year = {2026}, eprint = {2606.31672}, archiveprefix = {arXiv} } @inproceedings{duan2025worldscore, title = {{WorldScore}: A Unified Evaluation Benchmark for World Generation}, author = {Duan, Haoyi and Yu, Hong-Xing and Chen, Sirui and Fei-Fei, Li and Wu, Jiajun}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, year = {2025}, pages = {27713--27724}, doi = {10.1109/iccv51701.2025.02573} } @inproceedings{qin2024worldsimbench, title = {{W}orld{S}im{B}ench: Towards Video Generation Models As World Simulators}, author = {Qin, Yiran and Shi, Zhelun and Yu, Jiwen and Wang, Xijun and Zhou, Enshen and Li, Lijun and Yin, Zhenfei and Liu, Xihui and Sheng, Lu and Shao, Jing and Bai, Lei and Zhang, Ruimao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, year = {2025}, volume = {267}, pages = {50338--50362}, } @inproceedings{liuworldweaver, title = {WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception}, author = {Liu, Zhiheng and Deng, Xueqing and Chen, Shoufa and Wang, Angtian and Guo, Qiushan and Han, Mingfei and Xue, Zeyue and Chen, Mengzhao and Luo, Ping and Yang, Linjie}, booktitle = {Advances in Neural Information Processing Systems}, year = {2025}, volume = {38}, pages = {46268--46293}, doi = {10.52202/085713-1540} } @inproceedings{ma2022xclip, title = {X-CLIP: End-to-End Multi-Grained Contrastive Learning for Video-Text Retrieval}, author = {Ma, Yiwei and Xu, Guohai and Sun, Xiaoshuai and Yan, Ming and Zhang, Ji and Ji, Rongrong}, booktitle = {ACM International Conference on Multimedia (ACM MM)}, year = {2022}, pages = {638--647}, doi = {10.1145/3503161.3547910} } @misc{zheng2026xworld, title = {X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving}, author = {Chaoda Zheng and Sean Li and Jinhao Deng and Zhennan Wang and Shijia Chen and Liqiang Xiao and Ziheng Chi and Hongbin Lin and Kangjie Chen and Boyang Wang and Yu Zhang and Xianming Liu}, year = {2026}, eprint = {2603.19979}, archiveprefix = {arXiv} } @inproceedings{cheng2022xmem, title = {XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model}, author = {Ho Kei Cheng and Alexander G. Schwing}, booktitle = {Computer Vision -- ECCV 2022}, year = {2022}, doi = {10.1007/978-3-031-19815-1_37} } @misc{youtubevos2018, title = {YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark}, author = {Ning Xu and Linjie Yang and Yuchen Fan and Dingcheng Yue and Yuchen Liang and Jianchao Yang and Thomas Huang}, year = {2018}, eprint = {1809.03327}, archiveprefix = {arXiv} } @inproceedings{yume2025, title = {Yume1.5: A Text-Controlled Interactive World Generation Model}, author = {Mao, Xiaofeng and Li, Zhen and Li, Chuanhao and Xu, Xiaojie and Ying, Kaining and Zhang, Kaipeng}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2026}, pages = {7752--7761}, }