2 papers
cs.AI2026
Mismatch Matters: On-Policy Distillation Beyond Token Agreement
Zichao Yu, Chengzhi Yu, Shengze Xu +4
On-policy distillation (OPD) has emerged as a core component of modern LLM post-training pipelines, yet we reveal a failure mode: degenerate agreement, where students exploit repet…
cs.CL2026
Relative Score Policy Optimization for Diffusion Language Models
Zichao Yu, Shengze Xu, Bingqing Jiang +2
Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. R…