让扩散模型生成更多样样本，通过调整采样分布实现。
Variance-Tilted Diffusion Models for Diverse Sampling
- 引入方差加权批次分布，提升样本间差异性。
- 采样结果在特征空间中方差显著增大，多样性明显提升。
- 适合需要多样化输出的生成任务，如图像创作、内容推荐。
扩散模型通常独立采样，但下游任务常需多样化的候选结果。本文提出一种方差加权的批量分布，偏好经过指定线性特征映射后具有较大经验方差的样本集合。目标明确给出，采样器作为独立扩散动力学对应的Doob h-变换推导得出。修正项形式简洁：一个排斥后验去噪均值的相互作用项，以及一个将粒子引导至特征方差更高区域的曲率项。该方法构建了一个具有清晰概率目标的交互粒子采样器，而非启发式排斥漂移。
原文摘要 · Abstract (English)
Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weighted batch distribution that favours collections of samples with large empirical spread after a prescribed linear feature map. The target is specified explicitly, and the sampler is derived as the corresponding Doob $h$-transform of independent diffusion dynamics. The resulting correction has a compact form: an interaction term that repels posterior denoised means, together with a curvature term that moves particles to the region of higher feature variance. This yields an interacting-particle sampler with a transparent probabilistic target rather than a heuristic repulsive drift.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。