[2606.06021] OPRD: On-Policy Representation Distillation
-->
Computer Science > Machine Learning
arXiv:2606.06021 (cs)
[Submitted on 4 Jun 2026]
Title:OPRD: On-Policy Representation Distillation
Authors:Shenzhi Yang, Guangcheng Zhu, Bowen Song, Haobo Wang, Mingxuan Xia, Xing Zheng, Yingfan Ma, Zhongqi Chen, Weiqiang Wang, Gang Chen<br>View a PDF of the paper titled OPRD: On-Policy Representation Distillation, by Shenzhi Yang and 9 other authors
View PDF<br>HTML (experimental)
Abstract:On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from Monte Carlo KL estimates over large vocabularies (e.g., Qwen's ~150k tokens) persists throughout training, and (2) it treats the teacher as a black-box, discarding all intermediate hidden states after the LM head. We propose On-Policy Representation Distillation (OPRD), which lifts distillation into hidden-state space by aligning student and teacher representations across selected layers on the same rollouts, bypassing the LM head entirely. Theoretically, OPRD eliminates sampling variance and provides richer per-layer structural information. Empirically, OPRD closes the student-teacher gap on AIME 2024/2025 and AIMO, while output-space OPD baselines plateau below the teacher. OPRD also trains 1.44x faster and uses 54% less memory than top-k OPD. Code: this https URL.
Subjects:
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as:<br>arXiv:2606.06021 [cs.LG]
(or<br>arXiv:2606.06021v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.06021
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Shenzhi Yang [view email]<br>[v1]<br>Thu, 4 Jun 2026 11:13:01 UTC (3,524 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled OPRD: On-Policy Representation Distillation, by Shenzhi Yang and 9 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.LG
next >
new<br>recent<br>| 2026-06
Change to browse by:
cs<br>cs.AI
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
IArxiv recommender toggle
IArxiv Recommender<br>(What is IArxiv?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)