ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion

ForcingBooster is a framework that adaptively allocates denoising steps to individual video patches in autoregressive diffusion models, allowing easy patches to stop early while difficult patches receive more refinement. This dynamic scheduling reduces the total number of denoising steps by about 50% and improves generation efficiency with negligible quality loss. The method requires only a lightweight routing module and works with most existing few‑step autoregressive diffusion models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• diffusion