← Back to all news
arXiv Machine Learning By Hejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi, Xiaomin Li, Rohit Jain, Alborz Geramifard

Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts

Read the original on arXiv Machine Learning →

The paper introduces Δ‑MOPD, a multi‑teacher on‑policy distillation method that transfers each teacher’s logit shift relative to its base policy, re‑anchored at the student’s frozen initialization. Δ‑MOPD is evaluated in two settings: common‑domain composition, where multiple teachers score a single student rollout, and routed‑domain distillation, where prompts are assigned to specialist teachers. Across experiments, Δ‑MOPD outperforms traditional endpoint supervision, especially when teacher signals are combined at a state, achieving higher accuracy and reducing performance gaps in phased routing scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 28

MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation

MOPD‑Router rethinks teacher routing in multi‑teacher on‑policy distillation by routing supervision over the full teacher pool at each token, eliminating the need for prompt‑level domain labels or a separate routing model. The framework offers a plug‑in interface for various metrics, and introduces ExpertAlign, which scores teachers based on how well their corrections reflect their specialized post‑training knowledge. Experiments on both unlabeled and domain‑labeled mixtures show that ExpertAlign outperforms existing methods, improving overall scores by up to 12.3% on unlabeled data and 7.8% on domain‑labeled data. whyItMatters":"Token‑level routing enables the use of complementary supervision across domains without relying on domain labels, leading to significant performance gains in multi‑teacher distillation settings."

By Tianze Xu, Yanzhao Zheng, Zhentao Zhang, Yuanqiang Yu, Chao Ma, Jihuai Zhu, Lelun Wu, Lyumanshan Ye, Pengfei Liu, Baohua Dong, Hangcheng Zhu, Ruohui Huang, Gang Yu
efficiency
More like this →
arXiv AI
Sep 25

Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD

The paper introduces Selective Supervision for Direct-OPD (S$^2$D-OPD), a refinement of Direct On-Policy Distillation that filters out states where the teacher’s policy change is minimal, as measured by the teacher‑reference Jensen‑Shannon divergence. By masking low‑divergence states and keeping only the top 10% of states per response, S$^2$D-OPD improves held‑out accuracy on AIME and HMMT benchmarks across multiple teacher‑student pairs without additional forward passes.

By Yibo Zhao, Zixuan Yang, Yunshi Lan, Xiang Li
reinforcement-learningefficiencybenchmarks
More like this →
arXiv Machine Learning
Oct 16

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Waypoint-OPD is a new on-policy distillation method that leverages an intermediate teacher checkpoint to compare early and late policy shifts in reinforcement learning. By gating the endpoint shift based on the directional agreement between these early and late shifts, the method suppresses conflicting updates and requires only one additional frozen-teacher scoring pass. Experiments with Qwen3-4B teachers and larger Qwen3 student models in mathematical and code reasoning tasks show that Waypoint-OPD consistently outperforms endpoint-only transfer across all six domain–student settings.

By Bingxi Hou, Guochao Jiang, Guofeng Quan, Weiqing Li, Wenfeng Feng, Guohua Liu, Yuewei Zhang
reinforcement-learningefficiency
More like this →
arXiv AI
Aug 11

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

arXiv:2608. 09447v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation.

By Zehao Chen, Gongxun Li, Tianxiang Ai, Yifei Li, Zixuan Huang, Wang Zhou, Tao Huang, Fuzhen Zhuang, Xianglong Liu, Jianxin Li, Deqing Wang, Yikun Ban
efficiency
More like this →