AI RESEARCH
Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
arXiv CS.CL
•
ArXi:2606.01026v1 Announce Type: new Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unused. Existing approaches either add heuristic or learned mechanisms to revise committed tokens, or remask them back to [MASK] before re-predicting; a principled sampler that directly revises visible tokens without auxiliary modules remains underexplored. We.