AI RESEARCH

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

arXiv CS.CV

ArXi:2604.20470v1 Announce Type: new Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose \textbf{DynamicRad}, a unified sparse-attention paradigm that grounds adaptive selection within a radial locality prior. DynamicRad