Faster Video Diffusion with Trainable Sparse Attention

Code and additional resources are available through the FastVideo project.

Recommended citation: Peiyuan Zhang*, Yongqi Chen*, Haofeng Huang*, Will Lin, Zhengzhong Liu, Ion Stoica, Eric P. Xing, Hao Zhang. (2025). "Faster Video Diffusion with Trainable Sparse Attention." NeurIPS 2025.
Download Paper