@inproceedings{hu-etal-2025-investigating,
    title = "Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models",
    author = "Hu, Rui  and
      Qiu, Delai  and
      Wei, Shuyu  and
      Zhang, Jiaming  and
      Wang, Yining  and
      Liu, Shengping  and
      Sang, Jitao",
    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.389/",
    pages = "7452--7463",
    ISBN = "979-8-89176-256-5"
}