Diffusion models are an important tool for generative modelling, serving as effective priors in applications such as imaging and protein design. A key challenge in applying diffusion models for downstream tasks is efficiently sampling from resulting posterior distributions, which can be addressed using Doob's h-transform. This work introduces a self-supervised algorithm for fine-tuning diffusion models by learning the optimal control, enabling amortised conditional sampling. Our method iteratively refines the control using a synthetic dataset resampled with path-based importance weights. We demonstrate the effectiveness of this framework on class-conditional sampling, inverse problems and reward fine-tuning for text-to-image diffusion models.
@article{arxiv.2502.04468,
title = {Iterative Importance Fine-tuning of Diffusion Models},
author = {Alexander Denker and Shreyas Padhy and Francisco Vargas and Johannes Hertrich},
journal= {arXiv preprint arXiv:2502.04468},
year = {2026}
}