Signals 4 · free daily AI digest

An ODE-based Sampler for Discrete Diffusion Models

Paper recorded by Signals 4 on 2026-10-29 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.LG · 机器学习 · first seen 2026-10-30

Abstract

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 exponentia

Read on arXiv →

#70 most recent of 703 cs.LG papers we have recorded · ↑ newer: world2vec: Mechanistic world models through latent dynamics learning · ↓ older: Difficulty Calibration Across Time for Membership Inference in Diffusi
Cite this page: An ODE-based Sampler for Discrete Diffusion Models: the #70 most recent of 703 cs.LG papers we have recorded (as of 2026-10-29). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/an-ode-based-sampler-for-discrete-diffusion-models.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions