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

NeurIPSSpotlight2025

Authors
Shuo Yang, Haocheng Xi, Yilong Zhao, Muyang Li, Jintao Zhang, Han Cai, Yujun Lin, Xiuyu Li, Chenfeng Xu, Kelly Peng, Jianfei Chen, Song Han, Kurt Keutzer, Ion Stoica
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

transformer attention diffusion video

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive