@inproceedings{fu-etal-2026-vismind,
    title = "{V}is{M}ind: Stateful Synthetic Dialogue for Visual Mid-Training",
    author = "Fu, Xinlong  and
      Zhou, Zihao  and
      Wang, Qiufeng",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.1158/",
    pages = "24493--24510",
    ISBN = "979-8-89176-462-0"
}