Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Shuo, Xi, Haocheng, Zhao, Yilong, Li, Muyang, Zhang, Jintao, Cai, Han, Lin, Yujun, Li, Xiuyu, Xu, Chenfeng, Chen, Jianfei, Han, Song, Keutzer, Kurt, Stoica, Ion
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2505.18875