arXiv 2609.36484 · cs.LG · 2026-09-29
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Hao Li, MeiJia Chen, Weijie Ren, Donghan Li, Zijun Tian, Jingchun Huang, Naibo Wang
机构待核实
在最新榜 #22 2026-W40 第 3 名 本站收录于 2026-10-21
一句话要点
在线策略蒸馏中，沿 RL 引起的隐藏表征变化方向外推，让学生模型更稳定地超越教师。
Extrapolates RL-induced hidden-representation residuals in on-policy distillation so students can surpass teachers more stably.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
主题与学科
同主题：高效训练与推理
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
- TokenRouter: Efficient Serving System for Token-Level LLM Routing ▲143
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 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。