arXiv 2610.26824 · cs.CL · 2026-10-19
SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum
Zhongxin Chen, Songhao Wu, Heng Cui, Cong Li, Xiao Zhou, Rui Yan
机构待核实
在最新榜 #242 本站收录于 2026-10-21
一句话要点
SpecMRL 用参数导出的谱基重排特征，让俄罗斯套娃式表示的前缀维度更好地承载关键信息。
SpecMRL reorganises features on a parameter-derived spectral basis so Matryoshka prefixes carry the most important information.
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 ▲251
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
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 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。