arXiv 2609.38169 · cs.CL · 2026-09-29
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
Bingchen Yao, Haobo Xu, Haokun Lin, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Zhenan Sun 等 9 人
Zhejiang University
在最新榜 #73 2026-W41 第 10 名 本站收录于 2026-10-21
一句话要点
STEPQuant 分析线性注意力循环状态量化误差在时间和空间上的影响，实现低精度状态存储。
STEPQuant studies where and when quantisation errors matter in linear-attention recurrent states, enabling low-precision state storage.
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。