做生成模型长尾覆盖或罕见样本生成的团队，无需额外训练就能提升模型对低密度区域的探索能力，建议直接参考其采样策略。
标准分类器引导的扩散模型倾向于生成高密度类均值附近的样本，导致对尾部罕见样本的覆盖不足。现有方法通过训练额外的低密度分类器来解决，但增加了计算成本。本文提出一种纯采样阶段的密度感知方法，无需额外训练，通过修改反向扩散动力学，利用分类器梯度将轨迹引向低置信区域，同时引导采样接近真实数据流形。在ImageNet 64x64分辨率下，该方法一致提升了ADM模型的召回率，同时保持可比的FID分数；在256x256分辨率下，视觉结果显示了不同引导组合的效果。这项工作为生成模型的长尾覆盖问题提供了一种轻量级解决方案。
Enhanced Low-Density Region Exploration in Classifier-Guided Diffusion Models Through Modified Reverse Diffusion Sampling
Diffusion models have emerged as state-of-the-art generative models for high-fidelity image synthesis, particularly in their classifier-free guided and classifier-guided forms. However, standard classifier guidance concentrates probability mass around high-density class mean, leading to poor coverage of rare samples in the tails of the class-conditional distributions. Recent work on diffusion-based tail sampling mitigates this by training an additional low-density-seeking classifier with a synthetic-vs-real discriminator, at the cost of additional networks and training. In parallel, a number of samplers and distillation techniques accelerate or refine diffusion sampling, but do not explicitly address long-tail coverage. We propose a purely sampling-time, density-aware extension of classifier-guided conditional diffusion model that targets low-density regions without any additional training. We have applied guidance at noisy images not on predicted noise like most diffusion models. Starting from a pretrained conditional diffusion model and classifier on ImageNet, we modify the guided reverse dynamics by steering trajectories toward low-confidence regions via the modified classifier gradient, and at each time step, we also guide the sampling process toward the predicted real image. 1st guidance helps explore low-probability samples, and 2nd guidance helps to generate samples to be close to the real data manifold. The proposed sampler consistently improves ADM model recall at 64x64 resolution while maintaining a comparable FID, and with a 256x256 ADM model, we showed the results visually with different combinations of both guidance. We also showed that standard ADM classifier guidance, combined with predicted real image guidance, helps generate high perceptual quality samples with a 256x256 ADM model on ImageNet.