加速扩散模型的关键，藏在一条没人看的通道里
训练扩散模型时，大家一直以为是额外的监督信号或更好的特征结构在起作用。这篇论文发现，真正被改变的是一条几乎没人注意的内部通道——AdaLN-Zero 残差门控，它控制着条件信息如何流入模型的主干。加速训练的方法会大幅重组这条通道，而且重组得越彻底，生成质量越好。研究者还提出一个不需要额外教师模型的简单训练目标，只靠约束特征范数就能让门控参与更均匀，在 ImageNet 上比现有方法生成质量更好。它不是你明天能用上的东西，但它提醒你：AI 提速的秘密，可能藏在最不起眼的内部机制里。
📄 原文摘要(英文)
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly explained by additional supervision, spatial-structure priors, or improved feature geometry. We revisit this view and uncover a striking internal change: the AdaLN-Zero residual gate α, which directly controls how conditioned updates enter the residual stream, is substantially reorganized by these methods. This observation motivates our hypothesis that acceleration arises, at least in part, from reshaping the residual gating pathway rather than solely from the feature structures explicitly imposed by auxiliary objectives. Supporting this view, accelerated models are markedly more sensitive to perturbations of α, and their gate geometry reflects semantic relationships among classes. We further introduce the normalized participation ratio (nPR) to characterize the channel-wise organization of the gates and find that, across REPA teachers, projector architectures, and radial-objective targets, broader gate participation accompanies better generation quality. Guided by this insight, we propose a simple teacher-free radial objective that promotes broader gate participation through feature-norm regularization, without pairwise feature comparisons. On ImageNet 256times256 with SiT-B/2, our method improves FID over dispersive loss while increasing mean gate participation over timesteps and classes, further supporting the link between gate organization and training acceleration. Our results identify residual-gate reorganization as a measurable axis of diffusion training acceleration and suggest a simple direction for further acceleration.