【论文速递】An ODE-based Sampler for Discrete Diffusion Models

英文标题：An ODE-based Sampler for Discrete Diffusion Models

arXiv编号：2610.40618
作者：Samson Gourevitch, Yazid Janati, Eric Moulines
来源：arXiv
原文链接：https://arxiv.org/abs/2610.40618

中文摘要：
The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated sampling and consistency distillation. In this paper we address the question whether an analogous formulation exists for discrete diffusion models and answer it affirmatively by introducing exponential residual flows (ERFs). Our framework augments the discrete state with a continuous residual variable for each token and position. These residuals evolve deterministically according to piecewise-defined ODEs whose vector fields depend on the current discrete state and the forward and backward rate matrices of the prescribed diffusion model. The discrete state changes whenever a residual reaches zero. We prove that this construction preserves the marginals of the original diffusion. We derive a practical discretization of our sampler and specialize it to masked and uniform diffusion. The deterministic trajectories of ERFs support consistency distillation and yield empirical improvements over previous approaches across a variety of benchmarks including code and text generation tasks.

本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。