See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models
Policy gradient methods are widely used to align large language model outputs with human preferences, but the log-likelihoods they require cannot be directly computed in Masked Diffusion Language Models (MDLMs).
By Yunzhen He, Hiroaki Yamagiwa, Hidetoshi ShimodairaarXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Nov 16, 2026.
Comments
Sign in to join the discussion.