arXiv 2610.27450 · cs.AI · 2026-10-20
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation
Jiashuo Sun, Hao Zhang, Xueqiang Xu, Heng Wang, Yixuan Xie, Pengcheng Jiang, Zhenrui Yue, Jiajun Fan 等 12 人
University of Illinois at Urbana-Champaign
在最新榜 #342 本站收录于 2026-10-25
一句话要点
UIUC 的 Ask-to-Distill 学习为在线策略蒸馏合成训练题：把题目当作暴露教师知识的载体，用冻结的师生模型算出无需标准答案的题目价值替代指标，据此优化出题器。
UIUC's Ask-to-Distill learns to synthesize questions for on-policy distillation, scoring question value with a reference-free distributional surrogate from a frozen student-teacher pair and optimizing a student-initialized synthesizer on it.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库
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
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
同主题：大语言模型
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
同机构：University of Illinois at Urbana-Champaign
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 2026-10-26。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。