这篇论文发现了现有扩散蒸馏方法在CFG下的一个隐蔽问题，并给出了一个简单的修正方案。做扩散模型蒸馏或视频生成的同学可以看看。
本文研究在策略蒸馏（OPD）中分类器自由引导（CFG）的作用。现有OPD方法直接匹配教师和学生模型的引导速度，但在分支级别存在欠辨识问题：正负分支误差可相互补偿。作者发现，在共享负条件时匹配仍有效，但当教师负分支包含学生无法获取的特权信息时，会导致负分支不对称（NBA）失败模式。为解决NBA，提出正方向匹配（PDM），分别约束正预测和CFG条件方向。将PDM应用于稠密到稀疏视频控制，比朴素引导匹配更鲁棒有效。
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negative-branch errors can compensate in the guided prediction. Through two contrasting cases, we find that naive matching remains effective under shared negative conditioning, where both branch errors decrease jointly. When the model's native CFG schema retains privileged information in the teacher's negative branch that is unavailable to the student, however, this joint reduction breaks down and the composed objective induces antagonistic branch-error dynamics, reducing the positive-branch error while increasing the negative-branch error. We term this failure mode Negative Branch Asymmetry (NBA). To address NBA, we introduce Positive--Direction Matching (PDM), a branch-aware OPD objective that separately constrains the positive prediction and the CFG conditional direction. We apply PDM to dense-to-sparse video control, where naive guided matching is highly sensitive to inference guidance scales, while branch-aware supervision enables more robust and effective knowledge transfer.