@inproceedings{zhao-etal-2025-iam,
    title = "{IAM}: Efficient Inference through Attention Mapping between Different-scale {LLM}s",
    author = "Zhao, Yi  and
      Li, Zuchao  and
      Zhao, Hai",
    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.959/",
    pages = "19522--19533",
    ISBN = "979-8-89176-251-0"
}