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。

2025-10-07 至 2025-10-07 共收录 5 篇信号源：cs.CV, eess.IV, cs.MM

1. 视频理解 5 篇

2509.24008 2025-10-07 cs.CV cs.AI 79%

FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning

Haonan Ge, Yiwei Wang, Kai-Wei Chang, Hang Wu, Yujun Cai

机构 * University of California, Merced（加州大学默塞德分校）； University of California, Los Angeles（加州大学洛杉矶分校）； The University of Queensland（昆士兰大学）

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

Comments Underreview

2510.04401 2025-10-07 cs.CV cs.AI 57%

Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting

Xuyang Guo, Zekai Huang, Zhenmei Shi, Zhao Song, Jiahao Zhang

机构 * Guilin University of Electronic Technology（桂林电子科技大学）； The Ohio State University（俄亥俄州立大学）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； University of California, Berkeley（加州大学伯克利分校）

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

2510.03955 2025-10-07 cs.CV 57%

Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs

Sameep Vani, Shreyas Jena, Maitreya Patel, Chitta Baral, Somak Aditya, Yezhou Yang

机构 * Arizona State University（亚利桑那州立大学）； Indian Institute of Technology, Kharagpur（印度理工学院，克拉格浦）

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

Comments 17 pages, 9 figures, 6 tables. Presents TimeWarp, a synthetic preference data framework to improve temporal understanding in Video-LLMs, showing consistent gains across seven benchmarks. Includes supplementary material in the Appendix

2510.03706 2025-10-07 cs.RO cs.AI cs.CV cs.LG 57%

EmbodiSwap for Zero-Shot Robot Imitation Learning

Eadom Dessalene, Pavan Mantripragada, Michael Maynord, Yiannis Aloimonos

机构 * department of Computer Science, University of Maryland, College Park, MD, 20742（计算机科学系，马里兰大学， College Park, MD）

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

Comments Video link: https://drive.google.com/file/d/1UccngwgPqUwPMhBja7JrXfZoTquCx_Qe/view?usp=sharing

2507.11336 2025-10-07 cs.CV 57%

UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarks

Peiran Wu, Yunze Liu, Zhengdong Zhu, Enmin Zhou, Junxiao Shen

机构 * University of Bristol（布里斯托大学）； Memories.ai Research（Memories.ai研究）

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