Hugging Face Daily Papers·· 29 days agoAI score22
ALLOT: A training-free block sparse attention allocation method for video diffusion transformers
Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers
AI briefing
Researchers proposed a training-free sparse allocation method, ALLOT, which treats the combination of each layer and each denoising step as a unit, estimates its contribution to the final video error through unit probing and trajectory calibration, and jointly optimizes the density of each unit under a measured latency budget.
Open original arxiv.org