@inproceedings{jia-etal-2025-visualwebinstruct,
    title = "{V}isual{W}eb{I}nstruct: Scaling up Multimodal Instruction Data through Web Search",
    author = "Jia, Yiming  and
      Li, Jiachen  and
      Yue, Xiang  and
      Li, Bo  and
      Nie, Ping  and
      Zou, Kai  and
      Chen, Wenhu",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.emnlp-main.72/",
    pages = "1373--1393",
    ISBN = "979-8-89176-332-6"
}