@inproceedings{liu-etal-2026-tom,
    title = "{T}o{M}-Video: A Theory-of-Mind Video Benchmark with Spatio-Temporal Grounded Reasoning",
    author = "Liu, Quanling  and
      Lin, Zizhuo  and
      Quan, Jinsheng  and
      Shi, Xin  and
      Zhang, Xueqiao  and
      Zhang, Chao  and
      Zhu, Yifan  and
      Li, Zhihui  and
      Luo, Yawei",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.302/",
    pages = "6944--6972",
    ISBN = "979-8-89176-459-0"
}