@inproceedings{wang-etal-2026-vision,
    title = "Do Vision Language Models Understand Human Engagement in Games?",
    author = "Wang, Ziyi  and
      Guo, Qizan  and
      Singh, Rishitosh Kumar  and
      Hu, Xiyang",
    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.1636/",
    pages = "37184--37201",
    ISBN = "979-8-89176-459-0"
}