On-Policy Residual Learning for Diffusion Language Models
Residual context is key to unlocking the speed-quality Pareto frontier of diffusion language models (DLMs) by carrying forward predictive distributions across denoising steps.
By Yifan Yu, Yuqing Jian, Jisen Li, Yuezhou Hu, Tianyi Zhang, Xiaoxia Wu, Rui-Jie Zhu, Junxiong Wang, Zhongzhu Zhou, Fan Lai, James Zou, Chenfeng XuarXiv cs.LG
Read the full story
Originally published by arXiv cs.LG on Oct 16, 2026.
Comments
Sign in to join the discussion.