Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search
arXiv:2610.21129v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) dominate video generation but suffer from high inference cost due to the quadratic complexity of self-attention. Sparse attention mitigates this by skipping unnecessary computation in the attention matrix, but existing me…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv cs.CV
Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search