@inproceedings{wang-etal-2025-videollm,
    title = "{V}ideo{LLM} Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format",
    author = "Wang, Yueqian  and
      Meng, Xiaojun  and
      Wang, Yuxuan  and
      Liang, Jianxin  and
      Wei, Jiansheng  and
      Zhang, Huishuai  and
      Zhao, Dongyan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-emnlp.336/",
    pages = "6338--6359",
    ISBN = "979-8-89176-335-7"
}