@inproceedings{oh-etal-2024-preserving,
    title = "Preserving Multi-Modal Capabilities of Pre-trained {VLM}s for Improving Vision-Linguistic Compositionality",
    author = "Oh, Youngtaek  and
      Cho, Jae Won  and
      Kim, Dong-Jin  and
      Kweon, In So  and
      Kim, Junmo",
    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/fix-sig-urls/2024.emnlp-main.1062/",
    doi = "10.18653/v1/2024.emnlp-main.1062",
    pages = "19060--19076"
}