arXiv 2609.35347 · cs.LG · 2026-09-28
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation
Xin Li, Hao Jiang, Xin Gao, Annan Wang, Yuchen Xie, Jinghao Guo, Xingwei Qu, Yichi Zhang 等 9 人
Nanyang Technological University
在最新榜 #47 本站收录于 2026-10-21
一句话要点
多教师在线蒸馏中按领域归一化各教师的反馈强度，让学生同时学好数学、代码和指令遵循。
Normalises each teacher's feedback strength by domain in multi-teacher on-policy distillation so one student learns maths, code and instruction following.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
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 ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- 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。