Faster Video Diffusion with Trainable Sparse Attention
Published in NeurIPS 2025, 2025
Code and additional resources are available through the FastVideo project.
Recommended citation: Peiyuan Zhang*, Yongqi Chen*, Haofeng Huang*, Zhengzhong Liu, Ion Stoica, Eric Xing, Hao Zhang. (2025). "Faster Video Diffusion with Trainable Sparse Attention." NeurIPS 2025.
Download Paper