Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
We introduce ForcingBooster, an adaptive patch-wise denoising framework for autoregressive video diffusion models that addresses computational inefficiency by dynamically allocating denoising steps based on spatial content heterogeneity. By allowing easy patches to stop early and difficult patches to receive more refinement, the method significantly accelerates generation while preserving visual quality. Experiments show a ~50% reduction in total denoising steps compared to a four-step baseline with negligible quality degradation.
Static video regions can be denoised 50% faster without sacrificing quality by dynamically skipping computation on easy patches.
Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce \methodname{}, a general framework that dynamically allocates denoising steps to individual patches: easy patches stop early to improve efficiency, while difficult patches receive more refinement steps. This design accelerates generation with negligible quality degradation. Our method is compatible with most existing few-step autoregressive diffusion models, requiring only a lightweight routing module with modest training. Experiments demonstrate that \methodname{} reduces the total number of denoising steps applied across video patches by about 50\% while maintaining visual quality comparable to the four-step baseline.