@inproceedings{chen-etal-2025-vqaguider,
    title = "{VQAG}uider: Guiding Multimodal Large Language Models to Answer Complex Video Questions",
    author = "Chen, Yuyan  and
      Jia, Jiyuan  and
      Lu, Jiaxin  and
      Li, Siyue  and
      Guan, Yu  and
      Yang, Ming  and
      Guo, Qingpei",
    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.385/",
    pages = "7821--7834",
    ISBN = "979-8-89176-251-0"
}