MonkeyOCR: document parsing with a structure-recognition-relation triplet paradigm
Science China Information Sciences · 2026-11 · 69 (11)
DOI: 10.1007/s11432-026-5121-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science China Information Sciences, online erschienen am 03.11.2026. Verfasst von Zhang Li und 10 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We introduceMonkeyOCR, a document parsing model that advances the state of the art by leveraging a structure-recognition-relation (SRR) triplet paradigm. This design simplifies what would otherwise be a complex multi-tool pipeline and avoids the inefficiencies of processing full pages with giant end-to-end models. In SRR, document parsing is abstracted into three fundamental questions—“Where is it?” (structure), “What is it?” (recognition), and “How is it organized?” (relation)—corresponding to structure detection, content recognition, and relation prediction. To support this paradigm, we present MonkeyDoc, a comprehensive dataset with 4.5 million bilingual instances spanning over ten document types, which addresses the limitations of existing datasets that often focus on a single task, language, or document type. Leveraging the SRR paradigm and MonkeyDoc, we trained a 3B-parameter document foundation model. We further identify parameter redundancy in this model and propose contiguous parameter degradation (CPD), enabling the construction of models from 0.6B to 1.2B parameters that run faster with an acceptable performance drop. MonkeyOCR achieves state-of-the-art performance, surpassing previous open-source and closed-source methods, including Gemini 2.5 Pro. Additionally, the model can be efficiently deployed for inference on a single RTX 3090 GPU. Code and models will be released at https://github.com/Yuliang-Liu/MonkeyOCR .
Zitieren
APA
Li, Z., Liu, Y., Liu, Q., Ma, Z., Zhang, Z., Zhang, S., Yang, B., Guo, Z., Zhang, J., Wang, X., & Bai, X. (2026). MonkeyOCR: document parsing with a structure-recognition-relation triplet paradigm. Science China Information Sciences, 69(11). https://doi.org/10.1007/s11432-026-5121-6
Vancouver
Li Z, Liu Y, Liu Q, Ma Z, Zhang Z, Zhang S, et al. MonkeyOCR: document parsing with a structure-recognition-relation triplet paradigm. Science China Information Sciences. 2026;69(11). doi:10.1007/s11432-026-5121-6
BibTeX
@article{Li2026,
author = {Li, Zhang and Liu, Yuliang and Liu, Qiang and Ma, Zhiyin and Zhang, Ziyang and Zhang, Shuo and Yang, Biao and Guo, Zidun and Zhang, Jiarui and Wang, Xinyu and Bai, Xiang},
title = {MonkeyOCR: document parsing with a structure-recognition-relation triplet paradigm},
journal = {Science China Information Sciences},
year = {2026},
volume = {69},
number = {11},
doi = {10.1007/s11432-026-5121-6}
}
EUVIMED