@inproceedings{zhang-etal-2025-clusterattn,
    title = "{C}luster{A}ttn: {KV} Cache Compression under Intrinsic Attention Clustering",
    author = "Zhang, Minwei  and
      Sun, Haifeng  and
      Wang, Jingyu  and
      Li, Shaolong  and
      Ning, Wanyi  and
      Qi, Qi  and
      Zhuang, Zirui  and
      Liao, Jianxin",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.703/",
    pages = "14451--14473",
    ISBN = "979-8-89176-251-0"
}