"A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary ..."

Junhui He et al. (2025)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2502.12665

access: open

type: Informal or Other Publication

metadata version: 2025-04-01

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2502-12665
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2502-12665
Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li:
A²ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization. CoRR abs/2502.12665 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.