@inproceedings{li-etal-2025-mobilora,
    title = "{M}obi{L}o{RA}: Accelerating {L}o{RA}-based {LLM} Inference on Mobile Devices via Context-aware {KV} Cache Optimization",
    author = "Li, Borui  and
      Wang, Yitao  and
      Ma, Haoran  and
      Chen, Ligeng  and
      Xiao, Jun  and
      Wang, Shuai",
    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.1140/",
    pages = "23400--23410",
    ISBN = "979-8-89176-251-0"
}