English

Unlocking Guidance for Discrete State-Space Diffusion and Flow Models

Machine Learning 2025-03-27 v4

Abstract

Generative models on discrete state-spaces have a wide range of potential applications, particularly in the domain of natural sciences. In continuous state-spaces, controllable and flexible generation of samples with desired properties has been realized using guidance on diffusion and flow models. However, these guidance approaches are not readily amenable to discrete state-space models. Consequently, we introduce a general and principled method for applying guidance on such models. Our method depends on leveraging continuous-time Markov processes on discrete state-spaces, which unlocks computational tractability for sampling from a desired guided distribution. We demonstrate the utility of our approach, Discrete Guidance, on a range of applications including guided generation of small-molecules, DNA sequences and protein sequences.

Keywords

Cite

@article{arxiv.2406.01572,
  title  = {Unlocking Guidance for Discrete State-Space Diffusion and Flow Models},
  author = {Hunter Nisonoff and Junhao Xiong and Stephan Allenspach and Jennifer Listgarten},
  journal= {arXiv preprint arXiv:2406.01572},
  year   = {2025}
}
R2 v1 2026-06-28T16:51:38.994Z