数据来源：HuggingFace Papers

Latest Papers

1. OPRD: On-Policy Representation Distillation

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.

中文摘要

翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”

LLM Analysis

LLM Analysis Failed: Error: 抓取失败（已重试2次）: Navigation timeout of 10000 ms exceeded

Authors: Shenzhi Yang,Guangcheng Zhu,Bowen Song,Haobo Wang,Mingxuan Xia,Xing Zheng,Yingfan Ma,Zhongqi Chen,Weiqiang Wang,Gang Chen

PDF URL: https://arxiv.org/pdf/2606.06021.pdf

Arxiv URL: https://arxiv.org/abs/2606.06021

Arxiv ID: 2606.06021

CoolPaper URL: https://papers.cool/arxiv/2606.06021

Published: 2026-06-05T01:52:37.189Z

Updated: 2026-06-05T01:52:37.189Z