@inproceedings{niu-etal-2026-mineru2,
    title = "{M}iner{U}2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing",
    author = "Niu, Junbo  and
      Liu, Zheng  and
      Gu, Zhuangcheng  and
      Wang, Bin  and
      Ouyang, Linke  and
      Zhao, Zhiyuan  and
      Chu, Tao  and
      He, Tianyao  and
      Wu, Fan  and
      Zhang, Qintong  and
      Jin, Zhenjiang  and
      Liang, Guang  and
      Zhang, Rui  and
      Zhang, Wenzheng  and
      Qu, Yuan  and
      Ren, Zhifei  and
      Sun, Yuefeng  and
      Tang, Zirui  and
      Niu, Boyu  and
      Zheng, Yuanhong  and
      Ma, Dongsheng  and
      Miao, Ziyang  and
      Dong, Hejun  and
      Qian, Siyi  and
      Zhang, Junyuan  and
      Wang, Fangdong  and
      Chen, Jingzhou  and
      Zhao, Xiaomeng  and
      Wei, Liqun  and
      Li, Wei  and
      Wang, Shasha  and
      Xu, RuiLiang  and
      Cao, Yuanyuan  and
      Chen, Lu  and
      Wu, Qianqian  and
      Gu, Huaiyu  and
      Lu, Lindong  and
      Lin, Dechen  and
      Shenguanlin  and
      Zhou, Xuanhe  and
      Zhang, Linfeng  and
      Zang, Yuhang  and
      Dong, Xiaoyi  and
      Wang, Jiaqi  and
      Zhang, Bo  and
      Bai, Lei  and
      Chu, Pei  and
      Li, Weijia  and
      Wu, Jiang  and
      Wu, Lijun  and
      Li, Zhenxiang  and
      Wang, Guangyu  and
      Tu, Zhongying  and
      Xu, Chao  and
      Chen, Kai  and
      Zhou, Bowen  and
      Lin, Dahua  and
      Zhang, Wentao  and
      He, Conghui",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.3/",
    pages = "13--42",
    ISBN = "979-8-89176-394-4",
    abstract = "We introduce MinerU2.5, a 1.2B-parameter document parsing vision-language model that achieves state-of-the-art recognition accuracy while maintaining exceptional computational efficiency. Our approach employs a coarse-to-fine, two-stage parsing strategy that decouples global layout analysis from local content recognition. In the first stage, the model performs efficient layout analysis on downsampled images to identify structural elements, circumventing the computational overhead of processing high-resolution inputs. In the second stage, guided by the global layout, it performs targeted content recognition on native-resolution crops extracted from the original image, preserving fine-grained details in dense text, complex formulas, and tables. To support this strategy, we developed a comprehensive data engine that generates diverse, large-scale training corpora for both pretraining and fine-tuning. Ultimately, MinerU2.5 demonstrates strong document parsing ability, achieving state-of-the-art performance on multiple benchmarks, surpassing both general-purpose and domain-specific models across various recognition tasks, while maintaining significantly lower computational overhead."
}