@inproceedings{guo-etal-2026-beyond-seeing,
    title = "Beyond Seeing: Evaluating Multimodal {LLM}s on Tool-Enabled Image Perception, Transformation, and Reasoning",
    author = "Guo, Xingang  and
      Tyagi, Utkarsh  and
      Gosai, Advait  and
      Vergara, Paula  and
      Park, Jayeon  and
      Montoya, Ernesto Gabriel Hern{\'a}ndez  and
      Zhang, Chen Bo Calvin  and
      Hu, Bin  and
      He, Yunzhong  and
      Liu, Bing  and
      Srinivasa, Rakshith Sharma",
    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.1711/",
    pages = "38981--39048",
    ISBN = "979-8-89176-459-0"
}