视频大模型

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

Junpeng Ma, Qizhe Zhang, Ming Lu, Zhibin Wang, Qiang Zhou, Jun Song, Shanghang Zhang

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

Comments 10 pages, 3 figures

SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruning

Yicheng Ji, Jun Zhang, Heming Xia, Jinpeng Chen, Lidan Shou, Gang Chen, Huan Li

机构 * The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院） ； Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算机系） ； School of Computer Science, Beijing University of Posts and Telecommunications（北京邮电大学计算机学院） 纠错

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

Comments Accepted at EMNLP 2025 Main

Realistic and Controllable 3D Gaussian-Guided Object Editing for Driving Video Generation

Jiusi Li, Jackson Jiang, Jinyu Miao, Miao Long, Tuopu Wen, Peijin Jia, Shengxiang Liu, Chunlei Yu, Maolin Liu, Yuzhan Cai, Kun Jiang, Mengmeng Yang, Diange Yang

机构 * School of Vehicle and Mobility, and State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（车辆与移动系统学院，智能绿色车辆与移动系统国家重点实验室，清华大学） ； WUWEN AI ； PhiGent Robotics 纠错

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

Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics

Ruining Li, Chuanxia Zheng, Christian Rupprecht, Andrea Vedaldi

机构 * Visual Geometry Group, University of Oxford（牛津大学视觉几何组） 纠错

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

Comments Accepted at ICCV 2025. Project page: https://vgg-puppetmaster.github.io/

Unlearning Concepts from Text-to-Video Diffusion Models

Shiqi Liu, Yihua Tan

专题命中 视频扩散模型 ：video diffusion(title,abstract)；text-to-video(title,abstract)；video generation(abstract)；分类 cs.CV

Dress&Dance: Dress up and Dance as You Like It - Technical Preview

Jun-Kun Chen, Aayush Bansal, Minh Phuoc Vo, Yu-Xiong Wang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； SpreeAI 纠错

专题命中 视频扩散模型 ：video diffusion(abstract)；分类 cs.CV

Comments Project Page: https://immortalco.github.io/DressAndDance/

Ego-centric Predictive Model Conditioned on Hand Trajectories

Binjie Zhang, Mike Zheng Shou

专题命中 视频扩散模型 ：video generation(abstract)；分类 cs.CV

Comments Code: github.com/showlab/Ego-PM

MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation

Ming Chen, Liyuan Cui, Wenyuan Zhang, Haoxian Zhang, Yan Zhou, Xiaohan Li, Songlin Tang, Jiwen Liu, Borui Liao, Hejia Chen, Xiaoqiang Liu, Pengfei Wan

机构 * Kling Team, Kuaishou Technology（快手科技 Kling 团队） ； Zhejiang University（浙江大学） ； Tsinghua University（清华大学） 纠错

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

Comments Technical Report. Project Page: https://chenmingthu.github.io/milm/