Paper: Learning the Order of Thought in Diffusion Language Models

furongh · x · 2026-07-06

Released the paper "Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models," along with links to the paper, project page, and code. The authors suggest that the next frontier for diffusion language models may not just be learning the answer, but learning the order in which the answer should emerge. The paper is co-authored by Jimmy Xu, Minghao Liu, Aakriti, and others.

Related event: ICML 2026 Paper SAS: Optimizing Thought Scheduling in Diffusion LMs(15 posts)→

Original post →

More from Research

Research channel →