@inproceedings{zhang-etal-2025-sharper,
    title = "Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding",
    author = "Zhang, Daoze  and
      Zhao, Yuze  and
      Huang, Jintao  and
      Chen, Yingda",
    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.222/",
    pages = "4423--4439",
    ISBN = "979-8-89176-251-0"
}