AB-Attention加速视频扩散Transformer
AI 总结
Bin Xu等九位作者于2026年10月29日向arXiv提交论文“AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers”。该免训练方法结合块选择、包含概率加权与更细粒度的键值块聚合，在高稀疏度下近似稠密注意力。作者在Wan2.1和HunyuanVideo上报告跳过89%至92%的注意力计算，并实现最高2.23倍端到端加速。
深度见解
AB-Attention针对视频扩散Transformer推理中的二次注意力开销，其作者报告的Wan2.1与HunyuanVideo结果显示出可观的计算节省。
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.39663 (cs)
[Submitted on 29 Oct 2026]
Title:AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers
Authors:Bin Xu, Mo Zhang, Zhengfeiyang Zhang, Xinfeng Yang, Yixing Ma, Wei Wang, HeXin Wang, Pengfei Zhou, Wangbo Zhao
View a PDF of the paper titled AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers, by Bin Xu and 8 other authors