@inproceedings{sharma-etal-2024-losing,
    title = "Losing Visual Needles in Image Haystacks: Vision Language Models are Easily Distracted in Short and Long Contexts",
    author = "Sharma, Aditya  and
      Saxon, Michael  and
      Wang, William Yang",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-emnlp.312/",
    doi = "10.18653/v1/2024.findings-emnlp.312",
    pages = "5429--5451"
}