arXiv 2609.36322 · cs.LG · 2026-09-28
Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression
Xingyu Zhu, Pu, Yi, Ziheng Cheng, Ang Lv, Jing Liu, Lexing Ying, Yiyuan Ma 等 9 人
ByteDance Seed
在最新榜 #196 本站收录于 2026-10-21
一句话要点
发现分块 KV 缓存压缩带来“相位敏感”:信息在压缩窗口中的位置不同,检索准确率差异明显。
Finds chunked KV-cache compression causes phase sensitivity: retrieval accuracy varies with position relative to window boundaries.
阅读 arXiv 原文 PDF Hugging Face 讨论 项目页
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。