@inproceedings{collins-etal-2026-sketchvlm,
    title = "{S}ketch{VLM}: Vision language models can annotate images to explain thoughts and guide users",
    author = "Collins, Brandon  and
      Bolton, Logan  and
      Nguyen, Hung  and
      Taesiri, Mohammad Reza  and
      Bui, Trung  and
      Nguyen, Anh Totti",
    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.2449/",
    pages = "55534--55600",
    ISBN = "979-8-89176-459-0"
}