@inproceedings{he-etal-2025-a2ats,
    title = "{A}$^2${ATS}: Retrieval-Based {KV} Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization",
    author = "He, Junhui  and
      Xing, Junna  and
      Wang, Nan  and
      Xu, Rui  and
      Wu, Shangyu  and
      Zhou, Peng  and
      Liu, Qiang  and
      Xue, Chun Jason  and
      Li, Qingan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.findings-acl.644/",
    doi = "10.18653/v1/2025.findings-acl.644",
    pages = "12451--12463",
    ISBN = "979-8-89176-256-5"
}