ALLOT allocates block-sparse attention for video diffusion transformers
Training-free ALLOT gains 11.8 dB PSNR on HunyuanVideo with XAttention at equal or shorter runtime.
46
- Mentions · 7d1
- Mentions · 30d2
- All mentions2
- First seenSep 28, 2026
- Last mentioned5d ago
Timeline
2 articles · newest firstPDMD: Projected Distribution Matching Distillation for Video Diffusion Models
PDMD stabilizes video diffusion distillation by filtering critic errors, beating DMD at 4 NFE.
46
Appears with
- Wan2.2ai model · 1
- MiniMaxorganization · 1
- HunyuanVideoai model · 1
- MiniMax-H3ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.