@inproceedings{yeo-etal-2025-mms,
    title = "{MMS}-{LL}a{MA}: Efficient {LLM}-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens",
    author = "Yeo, Jeong Hun  and
      Rha, Hyeongseop  and
      Park, Se Jin  and
      Ro, Yong Man",
    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.1065/",
    pages = "20724--20735",
    ISBN = "979-8-89176-256-5"
}