Реклама

Partition the Support, Reconstruct the Residual: Training-Free Sparse Attention for Video Generation and World Models

#Partition #Support #Reconstruct #Residual #Training-Free

arXiv:2608.18484v1 Announce Type: new Abstract: Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not by itself specify an executable sparse operator. Queries sharing a block route may have poorly overlapping supports, while retained…