训练扩散模型，先让一个“笨”模型当陪练
训练高质量扩散模型很贵，但这篇发现：先训练一个“笨”版本，再让强模型故意偏离它的预测去学，反而学得更好、更快。具体做法是，训练中途存一个早期检查点当“弱指导”，主模型每次去噪时，把目标从弱模型的预测往外推一点，逼自己补上弱模型没学会的部分。弱模型不用参与主模型的反向传播，用完就扔，推理时完全不带它。在 ImageNet-256 上，用大约一半的训练算力就超过了原版最好的图像质量；在 RAEv2 上，不额外加推理引导就拿到 FID 1.15。它不是你明天能直接用的工具，但指向一个反直觉的趋势：让 AI 自己教自己，笨老师也能带出好学生。
📄 原文摘要(英文)
Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided training method that uses a frozen weak denoiser to improve a stronger model without adding inference overhead. For each noisy input, Swift extrapolates the clean regression target away from the weak denoiser's prediction, amplifying components that remain underfit. The weak guide can be an early training checkpoint, requires no backpropagation during main-model training, and is discarded afterward. The resulting model retains the original sampler and supports both conditional and unconditional generation without label dropout or an unconditional branch. We explain this mechanism through a spectral analysis of finite-time population gradient flow in an RKHS. With an early-stopped weak guide, we prove that a nonempty range of extrapolation strengths yields strictly lower posterior-mean error than matched standard training, despite shifting the regression target away from the posterior mean. Experiments on CIFAR-10 and ImageNet-256 demonstrate improvements across model scales and representations. In one ImageNet-256 configuration, Swift surpasses the baseline's best FID using roughly half the total training compute, including guide preparation and training overhead. On RAEv2, it achieves FID 1.15 without inference-time guidance and 0.99 with guidance. These results establish target extrapolation as an effective approach to weak-to-strong diffusion training with efficient single-model inference.