@inproceedings{zhou-etal-2025-glimpse,
    title = "{GLIMPSE}: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?",
    author = "Zhou, Yiyang  and
      Li, Linjie  and
      Qiu, Shi  and
      Yang, Zhengyuan  and
      Zhao, Yuyang  and
      Han, Siwei  and
      He, Yangfan  and
      Li, Kangqi  and
      Ji, Haonian  and
      Zhao, Zihao  and
      Tong, Haibo  and
      Wang, Lijuan  and
      Yao, Huaxiu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1415/",
    pages = "27830--27844",
    ISBN = "979-8-89176-332-6"
}