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。

2025-09-22 至 2025-09-22 共收录 9 篇信号源：cs.CV, eess.IV, cs.MM

1. 视频理解 2 篇

2508.10215 2025-09-22 eess.IV cs.CV 81%

Data-Efficient Learning for Generalizable Surgical Video Understanding

Sahar Nasirihaghighi

机构 * Department of Information Technology (ITEC), University of Klagenfurt（信息科技系，克雷根弗特大学）

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

2509.15800 2025-09-22 cs.CV cs.AI 79%

ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video Understanding

Kehua Chen

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

Comments 10 pages, 2 figures

2. 视频生成 3 篇

2509.15496 2025-09-22 cs.CV 79%

Lynx: Towards High-Fidelity Personalized Video Generation

Shen Sang, Tiancheng Zhi, Tianpei Gu, Jing Liu, Linjie Luo

机构 * ByteDance（字节跳动）

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

Comments Lynx Technical Report

2509.15479 2025-09-22 cs.CV 79%

OpenViGA: Video Generation for Automotive Driving Scenes by Streamlining and Fine-Tuning Open Source Models with Public Data

Björn Möller, Zhengyang Li, Malte Stelzer, Thomas Graave, Fabian Bettels, Muaaz Ataya, Tim Fingscheidt

机构 * Technische Universität Braunschweig（布拉unsch维格技术大学）

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

2509.14476 2025-09-22 cs.CV cs.AI cs.MM 73%

AToken: A Unified Tokenizer for Vision

Jiasen Lu, Liangchen Song, Mingze Xu, Byeongjoo Ahn, Yanjun Wang, Chen Chen, Afshin Dehghan, Yinfei Yang

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

Comments 30 pages, 14 figures

3. 视频扩散模型 1 篇

2412.01064 2025-09-22 cs.CV cs.AI cs.LG cs.MM eess.IV 67%

FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait

Taekyung Ki, Dongchan Min, Gyeongsu Chae

机构 * KAIST（韩国科学技术院）； DeepBrain AI Inc.（DeepBrain AI公司）

专题命中视频扩散模型：video generation(abstract)；分类 cs.CV、eess.IV、cs.MM

Comments ICCV 2025. Project page: https://deepbrainai-research.github.io/float/

4. 动作与事件理解 1 篇

2509.15546 2025-09-22 cs.CV 70%

Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track

Ran Hong, Feng Lu, Leilei Cao, An Yan, Youhai Jiang, Fengjie Zhu

机构 * TEX AI, Transsion Holdings（TEX AI，Transsion Holdings）； Nanchang University（南昌大学）； ShanghaiTech University（上海科技大学）

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

Comments 6 pages, 2 figures

5. 长视频与时序推理 1 篇

2505.05467 2025-09-22 cs.CV cs.AI cs.CL 57%

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

Haibo Wang, Bo Feng, Zhengfeng Lai, Mingze Xu, Shiyu Li, Weifeng Ge, Afshin Dehghan, Meng Cao, Ping Huang

机构 * Apple（苹果公司）； Fudan University（复旦大学）

专题命中长视频与时序推理：video understanding(abstract)；分类 cs.CV

Comments Accepted by NeurIPS 2025

6. 视频数据与评测 1 篇

2503.11103 2025-09-22 cs.CV cs.AI 57%

Pruning the Paradox: How CLIP's Most Informative Heads Enhance Performance While Amplifying Bias

Avinash Madasu, Vasudev Lal, Phillip Howard

机构 * Intel Labs（英特尔实验室）； Oracle（Oracle公司）； Thoughtworks（Thoughtworks公司）

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