ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
Computer Science > Computer Vision and Pattern Recognition arXiv:2610.12625 (cs) [Submitted on 8 Oct 2026] Title: ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion Authors: Zekai Gu, Peng Wang, Jiahao Lu, Yongsen Mao, Cheng Lin, Yuan Liu.
计算机科学 > 计算机视觉与模式识别 arXiv:2610.12625 (cs) [提交于 2026 年 10 月 8 日] 标题：ForcingBooster：用于快速自回归视频扩散的自适应分块去噪。作者：Zekai Gu, Peng Wang, Jiahao Lu, Yongsen Mao, Cheng Lin, Yuan Liu。
Abstract: 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.
摘要：自回归视频扩散模型已成为实时交互式视频生成和视频世界建模的主流方法。然而，现有方法在生成下一个视频块时，通常在空间上均匀分配计算资源，使用相同的去噪计划和函数评估次数来更新所有分块。这忽略了视频内容的空间异质性：静态、简单或重复的区域通常更容易去噪，而其他区域则需要进一步细化或额外的上下文信息。
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.
因此，统一的预算会导致简单分块上的计算冗余，而减少固定步数则可能导致困难分块细化不足。我们引入了 \methodname{}，这是一个为各个分块动态分配去噪步数的通用框架：简单分块提前停止以提高效率，而困难分块则获得更多的细化步数。这种设计在几乎不降低质量的前提下加速了生成过程。
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.
我们的方法与大多数现有的少步自回归扩散模型兼容，仅需一个轻量级的路由模块，且训练成本适中。实验表明，\methodname{} 将视频分块中应用的去噪总步数减少了约 50%，同时保持了与四步基准相当的视觉质量。