Efficient Architectures for High Resolution Vision-Language Models

Miguel Carvalho; Bruno Martins

COLING 2025main0 citations

Efficient Architectures for High Resolution Vision-Language Models

Abstract

Vision-Language Models (VLMs) have recently experienced significant advancements. However, challenges persist in the accurate recognition of fine details within high resolution images, which limits performance in multiple tasks. This work introduces Pheye, a novel architecture that efficiently processes high-resolution images while training fewer parameters than similarly sized VLMs. Notably, Pheye achieves a high efficiency while maintaining strong performance, particularly in tasks that demand fine-grained image understanding and/or the handling of scene-text.

BibTeX

@inproceedings{carvalho-martins-2025-efficient,
    title = "Efficient Architectures for High Resolution Vision-Language Models",
    author = "Carvalho, Miguel  and
      Martins, Bruno",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.700/",
    pages = "10520--10530"
}