@inproceedings{wang-etal-2025-unifiedvisual,
    title = "{U}nified{V}isual: A Framework for Constructing Unified Vision-Language Datasets",
    author = "Wang, Pengyu  and
      Zhou, Shaojun  and
      Tan, Chenkun  and
      Wang, Xinghao  and
      Huang, Wei  and
      Ye, Zhen  and
      Li, Zhaowei  and
      Jiang, Botian  and
      Zhang, Dong  and
      Qiu, Xipeng",
    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://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1572/",
    pages = "30855--30887",
    ISBN = "979-8-89176-332-6"
}