SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
Paper
•
2601.16515
•
Published
•
15
Dongyun Zou
strangerTHU
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
updated
a model
4 months ago
dc-ai/dc-ae-lite-f32c32-diffusers
Organizations
upvoted
a
paper
6 days ago