Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
基于变分稳定Doob匹配的扩散模型推理时对齐
Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity of the reference model while enforcing desired properties at the inference time. A central mechanism for achieving such alignment is guidance, which modifies the sampling dynamics through an additional drift term. In this work, we introduce variationally…