@inproceedings{zhao-etal-2024-unifashion,
    title = "{U}ni{F}ashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation",
    author = "Zhao, Xiangyu  and
      Zhang, Yuehan  and
      Zhang, Wenlong  and
      Wu, Xiao-Ming",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.89/",
    doi = "10.18653/v1/2024.emnlp-main.89",
    pages = "1490--1507"
}