AI 大模型

视频大模型

视频理解、视频生成、视频语言模型和时序视觉推理。

2025-10-03 至 2025-10-03 共收录 8 篇信号源：cs.CV, eess.IV, cs.MM

1. 视频生成 5 篇

2510.02283 2025-10-03 cs.CV cs.AI 83%

Self-Forcing++: Towards Minute-Scale High-Quality Video Generation

Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh

机构 * University of Central Florida（中央佛罗里达大学）

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

Comments preprint

2510.01284 2025-10-03 cs.MM cs.CV cs.SD eess.AS 81%

Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation

Chetwin Low, Weimin Wang, Calder Katyal

机构 * Character AI ； Yale University（耶鲁大学）

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

2501.08316 2025-10-03 cs.CV cs.AI cs.LG 79%

Diffusion Adversarial Post-Training for One-Step Video Generation

Shanchuan Lin, Xin Xia, Yuxi Ren, Ceyuan Yang, Xuefeng Xiao, Lu Jiang

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

Comments ICML 2025

2506.10540 2025-10-03 cs.MA cs.CV 57%

AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation

Haoyuan Shi, Yunxin Li, Xinyu Chen, Longyue Wang, Baotian Hu, Min Zhang

机构 * Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳分校）； Alibaba International Digital Commerce, Hangzhou（阿里巴巴国际数字商业）

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

2412.02259 2025-10-03 cs.CV cs.AI 57%

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, Ser-Nam Lim

机构 * Hong Kong University of Science and Technology（香港科技大学）； Peking University（北京大学）； University of Hong Kong（香港大学）； NUS（南洋理工大学）； University of Central Florida（佛罗里达大学）； Everlyn AI

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

Comments Code: https://github.com/DuNGEOnmassster/VideoGen-of-Thought.git; Webpage: https://cheliosoops.github.io/VGoT/

2. 动作与事件理解 1 篇

2510.02287 2025-10-03 cs.CV 74%

MultiModal Action Conditioned Video Generation

Yichen Li, Antonio Torralba

机构 * MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）

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

3. 长视频与时序推理 1 篇

2506.09350 2025-10-03 cs.CV cs.AI cs.LG 85%

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Shanchuan Lin, Ceyuan Yang, Hao He, Jianwen Jiang, Yuxi Ren, Xin Xia, Yang Zhao, Xuefeng Xiao, Lu Jiang

专题命中长视频与时序推理：video generation(title,abstract)；video diffusion(abstract)；long video(abstract)；分类 cs.CV

Comments NeurIPS 2025

4. 视频数据与评测 1 篇

2509.15596 2025-10-03 cs.CV 57%

EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery

Gui Wang, Yang Wennuo, Xusen Ma, Zehao Zhong, Zhuoru Wu, Ende Wu, Rong Qu, Wooi Ping Cheah, Jianfeng Ren, Linlin Shen

机构 * School of Computer Science & Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）； School of Computer Science, University of Nottingham Ningbo China（诺丁汉大学宁波校区计算机科学学院）； Wenzhou Medical University（温州医科大学）； School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）

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

Comments Strong accept by NeurIPS2025 Reviewers and AC