Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview
Text-to-Video • Updated • 1.19k • 51
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
Veda: Scalable Video Diffusion via Distilled Sparse Attention
ICML 2026 · Video Diffusion · Sparse Attention
Veda is a learned sparse-attention method for video DiTs. A lightweight tile-score predictor, distilled from full attention, keeps only the attention tiles that matter and skips the rest with a hardware-aligned tile-sparse kernel.
datasets 0
None public yet