@inproceedings{hu-etal-2025-mplug,
    title = "m{PLUG}-{D}oc{O}wl2: High-resolution Compressing for {OCR}-free Multi-page Document Understanding",
    author = "Hu, Anwen  and
      Xu, Haiyang  and
      Zhang, Liang  and
      Ye, Jiabo  and
      Yan, Ming  and
      Zhang, Ji  and
      Jin, Qin  and
      Huang, Fei  and
      Zhou, Jingren",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.291/",
    pages = "5817--5834",
    ISBN = "979-8-89176-251-0",
    abstract = "Multimodel Large Language Models(MLLMs) have achieved promising OCR-free Document Understanding performance by increasing the supported resolution of document images. However, this comes at the cost of generating thousands of visual tokens for a single document image, leading to excessive GPU memory and slower inference times, particularly in multi-page document comprehension. In this work, to address these challenges, we propose a High-resolution DocCompressor module to compress each high-resolution document image into 324 tokens, guided by low-resolution global visual features. With this compression module, to strengthen multi-page document comprehension ability and balance both token efficiency and question-answering performance, we develop the DocOwl2 under a three-stage training framework: Single-image Pretraining, Multi-image Continue-pretraining, and Multi-task Finetuning. DocOwl2 sets a new state-of-the-art across multi-page document understanding benchmarks and reduces first token latency by more than 50{\%}. Compared to single-image MLLMs trained on similar data, our DocOwl2 achieves comparable single-page understanding performance with less than 20{\%} of the visual tokens. Our codes, models, and data will be publicly available."
}