@inproceedings{jiang-etal-2025-kvpr,
    title = "{KVPR}: Efficient {LLM} Inference with {I}/{O}-Aware {KV} Cache Partial Recomputation",
    author = "Jiang, Chaoyi  and
      Gao, Lei  and
      Zarch, Hossein Entezari  and
      Annavaram, Murali",
    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.997/",
    pages = "19474--19488",
    ISBN = "979-8-89176-256-5"
}