@inproceedings{jin-etal-2024-mmtom,
    title = "{MMT}o{M}-{QA}: Multimodal Theory of Mind Question Answering",
    author = "Jin, Chuanyang  and
      Wu, Yutong  and
      Cao, Jing  and
      Xiang, Jiannan  and
      Kuo, Yen-Ling  and
      Hu, Zhiting  and
      Ullman, Tomer  and
      Torralba, Antonio  and
      Tenenbaum, Joshua  and
      Shu, Tianmin",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.acl-long.851/",
    doi = "10.18653/v1/2024.acl-long.851",
    pages = "16077--16102"
}