works on
diffusion models 1multimodal language models 1multi-reference video editing 1reference tokens 1structured instructions 1

From the 1 of 16 linked papers with an AI index.

activity
20242026
collaborators
Showing cs.AIShow all

1 paper · 1 filter

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…