Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts
Paper recorded by Signals 4 on 2026-10-07 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-07 on arXiv · recorded by Signals 4 on 2026-10-08
Category: cs.AI · 人工智能 · first seen 2026-10-08
Abstract
Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-t
Read on arXiv →
Cite this page: Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts: the #393 most recent of 960 cs.AI papers we have recorded (as of 2026-10-07). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/composing-what-each-teacher-learned-multi-teacher-on-policy-distillation-through.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free