视频大模型

2505.01481 2025-10-28 cs.CV cs.LG 79%

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding

Zongxia Li, Xiyang Wu, Guangyao Shi, Yubin Qin, Hongyang Du, Fuxiao Liu, Tianyi Zhou, Dinesh Manocha, Jordan Lee Boyd-Graber

机构 * University of Maryland, College Park（马里兰大学学院公园分校）

专题命中视频理解：video understanding(title,abstract)；分类 cs.CV

Journal ref NeurIPS 2025

2510.23569 2025-10-28 cs.CV 57%

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Baoqi Pei, Yifei Huang, Jilan Xu, Yuping He, Guo Chen, Fei Wu, Yu Qiao, Jiangmiao Pang

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Zhejiang University（浙江大学）； The University of Tokyo（东京大学）； Fudan University（复旦大学）； Nanjing University（南京大学）

专题命中视频理解：video reasoning(abstract)；分类 cs.CV

Comments Accepted at NeurIPS 2025

2510.23473 2025-10-28 cs.CV 57%

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning

Shijian Wang, Jiarui Jin, Xingjian Wang, Linxin Song, Runhao Fu, Hecheng Wang, Zongyuan Ge, Yuan Lu, Xuelian Cheng

机构 * Southeast University（东南大学）； Monash University（墨尔本大学）； Xiaohongshu Inc.（小红书公司）； University of Southern California（南加州大学）； Fudan University（复旦大学）

专题命中视频理解：video reasoning(abstract)；分类 cs.CV

2510.23397 2025-10-28 cs.CV 57%

VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations

Lu Dong, Haiyu Zhang, Han Lin, Ziang Yan, Xiangyu Zeng, Hongjie Zhang, Yifei Huang, Yi Wang, Zhen-Hua Ling, Limin Wang, Yali Wang

机构 * University of Science and Technology of China（中国科学技术大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Beihang University（北京航空航天大学）； Shanghai Jiao Tong University（上海交通大学）； Zhejiang University（浙江大学）； State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）； Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）

专题命中视频理解：video understanding(abstract)；分类 cs.CV

2510.23007 2025-10-28 cs.CV 88%

CoMo: Compositional Motion Customization for Text-to-Video Generation

Youcan Xu, Zhen Wang, Jiaxin Shi, Kexin Li, Feifei Shao, Jun Xiao, Yi Yang, Jun Yu, Long Chen

机构 * Zhejiang University（浙江大学）； HKUST（香港科技大学）； Xmax.AI Ltd（Xmax人工智能有限公司）； HIT (SZ)（哈尔滨工业大学（深圳））

专题命中视频生成：video generation(title,abstract)；text-to-video(title,abstract)；分类 cs.CV

2507.04705 2025-10-28 cs.CV 86%

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations

Yuji Wang, Moran Li, Xiaobin Hu, Ran Yi, Jiangning Zhang, Han Feng, Weijian Cao, Yabiao Wang, Chengjie Wang, Lizhuang Ma

机构 * Shanghai Jiao Tong University, Tencent Youtu Lab（上海交通大学，腾讯云图实验室）； Tencent Youtu Lab（腾讯云图实验室）； Shanghai Jiao Tong University（上海交通大学）； Tencent（腾讯）

专题命中视频生成：text-to-video(title,abstract)；video generation(title)；分类 cs.CV

Comments ACM Multimedia 2025; code URL: https://github.com/rain152/IPVG

2510.22431 2025-10-28 cs.MA cs.CV 83%

Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration

Zheng Wei, Mingchen Li, Zeqian Zhang, Ruibin Yuan, Pan Hui, Huamin Qu, James Evans, Maneesh Agrawala, Anyi Rao

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学）； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））； University of Chicago（芝加哥大学）； Stanford University（斯坦福大学）

专题命中视频生成：video generation(title,abstract)；long video(abstract)；分类 cs.CV

2503.16421 2025-10-28 cs.CV cs.AI cs.LG cs.MM 81%

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

Quanhao Li, Zhen Xing, Rui Wang, Hui Zhang, Qi Dai, Zuxuan Wu

机构 * Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理关键实验室，复旦大学计算机学院）； Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）； Microsoft Research Asia（微软亚洲研究院）

专题命中视频生成：video generation(title,abstract)；分类 cs.CV、cs.MM

Comments Accepted by ICCV 2025

2501.13918 2025-10-28 cs.CV cs.AI cs.GR cs.LG 79%

Improving Video Generation with Human Feedback

Jie Liu, Gongye Liu, Jiajun Liang, Ziyang Yuan, Xiaokun Liu, Mingwu Zheng, Xiele Wu, Qiulin Wang, Menghan Xia, Xintao Wang, Xiaohong Liu, Fei Yang, Pengfei Wan, Di Zhang, Kun Gai, Yujiu Yang, Wanli Ouyang

机构 * MMLab, CUHK（CUHK媒体实验室）； Tsinghua University（清华大学）； Kling Team, Kuaishou Technology（快手科技 Kling 团队）； Shanghai Jiao Tong University（上海交通大学）； Shanghai AI Laboratory（上海人工智能实验室）

专题命中视频生成：video generation(title,abstract)；分类 cs.CV

Comments https://github.com/KwaiVGI/VideoAlign

2510.21840 2025-10-28 cs.CV cs.GR 74%

Improving the Physics of Video Generation with VJEPA-2 Reward Signal

Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat, Xiaochuang Han, Nicolas Ballas, Michal Drozdzal, Adriana Romero-Soriano

机构 * FAIR, Meta Superintelligence Labs（FAIR、Meta超智能实验室）； University of Oxford（牛津大学）； Mila - Québec AI Institute（魁北克人工智能研究所）； Université de Montréal（蒙特利尔大学）； Columbia University（哥伦比亚大学）； McGill University（麦吉尔大学）； Canada CIFAR AI Chair（加拿大CIFAR人工智能 chair）

专题命中视频生成：video generation(title)；分类 cs.CV

Comments 2 pages

Journal ref Winning entry of the ICCV 2025 Physics IQ Challenge

2503.14350 2025-10-28 cs.CV cs.AI cs.CL 57%

VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation

Shoubin Yu, Difan Liu, Ziqiao Ma, Yicong Hong, Yang Zhou, Hao Tan, Joyce Chai, Mohit Bansal

机构 * Adobe Research（Adobe研究机构）； University of Michigan（密歇根大学）； UNC Chapel Hill（北卡罗来纳大学教堂山分校）

专题命中视频生成：video diffusion(abstract)；分类 cs.CV

Comments ICCV 2025; First three authors contributed equally. Project page: https://veggie-gen.github.io/

2510.21991 2025-10-28 cs.RO cs.AI 50%

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Mateo Clemente, Leo Brunswic, Rui Heng Yang, Xuan Zhao, Yasser Khalil, Haoyu Lei, Amir Rasouli, Yinchuan Li

机构 * Huawei Technologies Canada（华为技术加拿大）

专题命中视频扩散模型：video generation(abstract)

Comments 16 pages, 11 figure, 2 tables, accepted at Neurips 2025

2506.17113 2025-10-28 cs.CV cs.AI cs.CL 57%

MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation

Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal

机构 * UNC Chapel Hill（北卡罗来纳大学教堂山分校）； Nanyang Technological University（南洋理工大学）

专题命中视频问答：video reasoning(abstract)；分类 cs.CV

Comments EMNLP 2025 Findings; The first two authors contributed equally; Github link: https://github.com/Yui010206/MEXA

2501.07227 2025-10-28 cs.CV 83%

MECD+: Unlocking Event-Level Causal Graph Discovery for Video Reasoning

Tieyuan Chen, Huabin Liu, Yi Wang, Yihang Chen, Tianyao He, Chaofan Gan, Huanyu He, Weiyao Lin

机构 * Shanghai Jiao Tong University（上海交通大学）； Monash University（墨尔本大学）； Zhongguancun Academy（中关村academy）； Shanghai AI Laboratory（上海人工智能实验室）

专题命中动作与事件理解：video reasoning(title)；video understanding(abstract)；long video(abstract)；分类 cs.CV

Comments Accepted by IEEE TPAMI (IEEE Transactions on Pattern Analysis and Machine Intelligence). arXiv admin note: substantial text overlap with arXiv:2409.17647

2510.22810 2025-10-28 cs.CV 70%

MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control

Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, Josef Kittler

机构 * School of Computer Science and Electronic Engineering, University of Surrey（Surrey大学计算机科学与电子工程学院）； School of Artificial Intelligence and Computer Science, Jiangnan University（江南大学人工智能与计算机科学学院）； Centre for Vision, Speech and Signal Processing, University of Surrey（Surrey大学视觉、语音和信号处理中心）

专题命中动作与事件理解：video generation(abstract)；long video(abstract)；分类 cs.CV

2510.23190 2025-10-28 cs.CV 57%

Evaluation of Vision-LLMs in Surveillance Video

Pascal Benschop, Cristian Meo, Justin Dauwels, Jelte P. Mense

机构 * Department of Computer Science（计算机科学系）； Delft University of Technology（代尔夫特理工大学）； LatentWorlds AI ； National Policelab AI & Model-Driven Decisions Lab（国家警务实验室AI与模型驱动决策实验室）

专题命中视频数据与评测：video understanding(abstract)；分类 cs.CV

Comments Accepted as poster in the NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI

1. 视频理解 4 篇