@inproceedings{yao-etal-2025-tailorkv,
    title = "{T}ailor{KV}: A Hybrid Framework for Long-Context Inference via Tailored {KV} Cache Optimization",
    author = "Yao, Dingyu  and
      Shen, Bowen  and
      Lin, Zheng  and
      Liu, Wei  and
      Luan, Jian  and
      Wang, Bin  and
      Wang, Weiping",
    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/landing_page/2025.findings-acl.1043/",
    pages = "20340--20359",
    ISBN = "979-8-89176-256-5"
}