@inproceedings{song-etal-2025-figex,
    title = "{F}ig{E}x: Aligned Extraction of Scientific Figures and Captions",
    author = "Song, Jifeng  and
      Das, Arun  and
      Cui, Ge  and
      Huang, Yufei",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.899/",
    doi = "10.18653/v1/2025.findings-emnlp.899",
    pages = "16558--16571",
    ISBN = "979-8-89176-335-7",
    abstract = "Automatic understanding of figures in scientific papers is challenging since they often contain subfigures and subcaptions in complex layouts. In this paper, we propose FigEx, a vision-language model to extract aligned pairs of subfigures and subcaptions from scientific papers. We also release BioSci-Fig, a curated dataset of 7,174 compound figures with annotated subfigure bounding boxes and aligned subcaptions. On BioSci-Fig, FigEx improves subfigure detection $AP^b$ over Grounding DINO by 0.023 and boosts caption separation BLEU over Llama-2-13B by 0.465. The source code is available at: https://github.com/Huang-AI4Medicine-Lab/FigEx."
}