提出杰弗里引导方法，让扩散模型更灵活地控制生成结果。
Towards More General Control of Diffusion Models Using Jeffrey Guidance
- 用杰弗里条件法则更新边缘分布，保持联合分布最小扰动
- 在CIFAR-10和FFHQ上使FID显著降低，目标为指定嵌入分布
- 适用于属性公平性等复杂控制场景，适合研究可控生成的学者
扩散模型的核心优势在于采样时可灵活控制输出。然而，除条件采样等简单情况外，目标分布常隐含于采样规则或启发式能量函数中。为此，我们提出杰弗里引导（Jeffrey guidance），一种可扩展标准引导的应用框架。它利用杰弗里的条件化规则，将边缘分布推向预定目标，同时保持条件结构不变，并最小化对联合分布的扰动。我们首先通过设定目标嵌入分布验证该方法：以Inception嵌入为目标，在CIFAR-10和FFHQ上均实现显著的FID下降。进一步应用于CelebA-HQ的公平性控制，将无条件扩散模型调整为强制属性间独立，有效提升生成结果的公平性。
原文摘要 · Abstract (English)
A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance. However, beyond simple cases such as conditional sampling, the target distribution is often left implicit, defined only through a sampling rule or a heuristic energy function. To address this, we propose Jeffrey guidance, a principled framework that extends diffusion-model control to applications beyond what standard guidance can express. It leverages Jeffrey's rule of conditioning to update marginal distributions towards a prescribed target, preserving the conditional structure and minimally perturbing the joint distribution. We first demonstrate Jeffrey guidance by targeting a prescribed embedding distribution. With Inception embeddings as the target, this leads to substantial reductions in FID on both CIFAR-10 and FFHQ. We further apply Jeffrey guidance to fairness on CelebA-HQ, updating an unconditional diffusion model to enforce independence between attributes.
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。