InstaGen：组共享重要性采样加速视频生成
原标题：InstaGen: Group-Shared Importance Sampling for Fast Video Generation
AI 摘要
该论文提出 InstaGen，一种用于加速视频生成的免训练稀疏注意力方法。作者发现现有 PBSA 方法采用 top-p 选择在高熵注意力场景下采样效率低，于是将块选择建模为重要性采样：对每个查询簇保留得分最高的精确块集合，其余键按估计注意力概率采样并用逆采样概率重加权。在 Wan2.1-T2V-1.3B 和 14B 上，InstaGen 在相同注意力密度下 PSNR 分别比 SVG2 提升 3.4 dB 和 2 dB，并实现全稀疏推理、消除稠密步骤。
正文节选
InstaGen: Group-Shared Importance Sampling for Fast Video Generation Abstract Diffusion Transformers (DiTs) are the dominant architecture for video generation, but their quadratic attention complexity results in substantial computational cost and latency. Permuted block-sparse attention (PBSA) offers a promising approach to reducing this cost by selectively computing blocks of a semantically permuted attention matrix. However, existing approaches typically select only the top few key blocks for