Veda: Scalable Video Diffusion via Distilled Sparse Attention 文章

ArXiv CS.CV2026-05-29NEWSen作者: Shihao Han, Hao Yang, Xinting Hu, Xiaofeng Mei, Yi Jiang, Xiaojuan Qi

查看原文 →

Veda: Scalable Video Diffusion via Distilled Sparse Attention · 相关技术

相关技术

EDA full attention tile-wise geometry Sparse Attention self-attention Diffusion Transformer