arXiv 2610.14022 · cs.LG · 2026-09-29
OPMD: On-Policy Mechanism Distillation Beyond Output Supervision
Yingdong Shi, Zhihong Li, Changming Li, Jingyi Yu, Quan Li, Kan Ren
ShanghaiTech University
在最新榜 #393 本站收录于 2026-10-25
一句话要点
上科大的 OPMD 把在线策略蒸馏从只监督输出扩展到传递教师的中间计算：先构造学生能用的教师中间状态，解决表征几何不一致和不可用的问题。
ShanghaiTech's OPMD extends on-policy distillation beyond outputs to transfer teacher intermediate computation, first building a student-compatible teacher whose intermediate states the student's downstream layers can actually use.
阅读 arXiv 原文 PDF Hugging Face 讨论
主题与学科
同主题：高效训练与推理
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。