arXiv · AI· Zixuan Huang (School of Computer Science, Peking University, Beijing, China, School of Physics, Peking University, Beijing, China), Tianhao You (School of Computer Science, Peking University, Beijing, China), Guozhang Chen (School of Computer Science, Peking University, Beijing, China, National Engineering Research Center of Visual Technology, Peking University, Beijing, China)·· 8 小时前AI 评分23
SFA：一种受统计物理启发的扩散Transformer，用于高效且高质量的图像生成
SFA: A Statistical Physics-Inspired Diffusion Transformer for Efficient and High-Quality Image Generation
AI 导读
北京大学团队提出受统计物理启发的Scale-Free Attention（SFA），将扩散Transformer中前向与反向传播的注意力复杂度优化至O(N log N)。
来源：arXiv · AI · arxiv.org