# AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers > Source: > Published: 2026-10-30 08:30:22+00:00 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 u