Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation

arXiv:2604.12219v1 Announce Type: cross Abstract: Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods frequently provoke severe visual flickering caused by static sparsity patterns and deterministic block routing. To resolve these limitations, we propose Precision-Allocated Sparse Attention (PASA), a training-free fram