Video diffusion transformers generate high-quality videos, but the quadratic cost of 3D full attention dominates their inference. Dynamic block-sparse attention reduces this cost by computing exact at
AB-Attention approximates dense video diffusion attention with high sparsity via intra-block clustering, weighted sampling, and fine-grained kernel gathering, improving fidelity and speed.
Video diffusion transformers generate high-quality videos, but the quadratic cost of 3D full attention dominates their inference. Dynamic block-sparse attention reduces this cost by computing exact attention only on key/value blocks selected from current activations. However, its fidelity degrades under aggressive sparsity: blocks are scored from coarse summaries or formed by costly global clustering, pruned blocks vanish from the softmax, and whole tiles are kept or dropped even when only a few of their keys matter. To address these limitations, we propose Accurate Block Attention (AB-Attention), a training-free method that accurately approximates dense attention at high sparsity. Its…
Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.
AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers was first seen on Hugging Face · Daily papers on Nov 2, 2026. Since then it has appeared in 5 checks on 1 different day. Its best position was #26 of 30, reached on Nov 2, 15:28 UTC. It dropped off the list after Nov 2, 17:28 UTC.
Position on Hugging Face · Daily papers at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hugging Face.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 2, 17:28 UTC, after 1 day of trending.
#26 on Hugging Face · Daily papers, on Nov 2, 15:28 UTC. Trendoday checks this list every 120 minutes.
It was first seen on Nov 2, 2026 and has been on the list on 1 day (5 checks) since.