Skip to content

A²ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization.

Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li

VenueA*ACL
Year2025
ProceedingsACL (Findings)

Browse the full ACL paper archive.