视频大模型 - arXivDaily 专题

2502.18137 2025-11-20 cs.LG cs.AI cs.CV cs.PF 57%

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference

Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, Jianfei Chen

机构 * Dept. of Comp. Sci. and Tech., Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint ML Center, Tsinghua University（计算机科学与技术系，人工智能研究所，BNRist中心，THBI实验室，清华-博世联合机器学习中心，清华大学）； Institute for Interdisciplinary Information Sciences, Tsinghua University（交叉信息学院，清华大学）； EECS, University of California, Berkeley（电子工程与计算机科学系，加州大学伯克利分校）

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

Comments @inproceedings{zhang2025spargeattn, title={Spargeattn: Accurate sparse attention accelerating any model inference}, author={Zhang, Jintao and Xiang, Chendong and Huang, Haofeng and Wei, Jia and Xi, Haocheng and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Machine Learning (ICML)}, year={2025} }

Journal ref Proceedings of the 42 nd International Conference on Machine Learning, PMLR 267, 2025 (ICML 2025)

1. 视频生成 1 篇

SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference