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
In latest · #393 Added on 2026-10-25
One-line takeaway
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.
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。
Read on arXiv PDF Hugging Face discussion
Topics & disciplines
More on Efficient training & inference
- 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
More on LLMs
- 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
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.