Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers
Paper • 2610.29441 • Published • 13 •
2
Tianze Xia
Makayi
·
AI & ML interests
None yet
Recent Activity
commentedon a paper 12 minutes ago
Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers authored a paper about 2 hours ago
Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers submitted a paper about 8 hours ago
Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion TransformersOrganizations
commented a
paper 12 minutes ago