@inproceedings{pantazopoulos-etal-2024-shaking,
    title = "Shaking Up {VLM}s: Comparing Transformers and Structured State Space Models for Vision {\&} Language Modeling",
    author = "Pantazopoulos, Georgios  and
      Nikandrou, Malvina  and
      Suglia, Alessandro  and
      Lemon, Oliver  and
      Eshghi, Arash",
    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/Author-page-Marten-During-lu/2024.emnlp-main.793/",
    doi = "10.18653/v1/2024.emnlp-main.793",
    pages = "14318--14337"
}