arXiv 2610.13521 · cs.AI · 2026-10-09
Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
Shi-Yu Tian, Yong Liu, Ximan Liu, Tianrui Zhu, Sule Bai, Xinwei Yang, Ruiqi Liu, Kun-Yang Yu 等 13 人
jingdong
在最新榜 #120 本站收录于 2026-10-21
一句话要点
在多教师在线蒸馏中加入跨教师“护栏”,减少不同领域教师之间的梯度冲突。
Adds cross-teacher guarding to multi-teacher on-policy distillation to reduce gradient conflicts between domain teachers.
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
- 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。