@inproceedings{li-etal-2025-jarvis,
    title = "{JARVIS}-{VLA}: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse",
    author = "Li, Muyao  and
      Wang, Zihao  and
      He, Kaichen  and
      Ma, Xiaojian  and
      Liang, Yitao",
    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/acl25-workshop-ingestion/2025.findings-acl.920/",
    pages = "17878--17899",
    ISBN = "979-8-89176-256-5"
}