MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns

TL;DR

MonkeyOCR v1.5 is a comprehensive document parsing system that improves layout understanding and content recognition in complex, real-world documents through a two-stage vision-language framework with novel modules and reinforcement learning.

Contribution

The paper introduces MonkeyOCR v1.5, a unified framework with a two-stage pipeline, reinforcement learning for table structure accuracy, and modules for handling embedded images and cross-page tables, advancing document parsing capabilities.

Findings

Achieves state-of-the-art performance on OmniDocBench v1.5

Outperforms PPOCR-VL and MinerU 2.5 in robustness and accuracy

Excels in complex document scenarios with multi-level tables and embedded images.

Abstract

Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. However, real-world documents often feature complex layouts with multi-level tables, embedded images or formulas, and cross-page structures, which remain challenging for existing OCR systems. We introduce MonkeyOCR v1.5, a unified vision-language framework that enhances both layout understanding and content recognition through a two-stage pipeline. The first stage employs a large multimodal model to jointly predict layout and reading order, leveraging visual information to ensure sequential consistency. The second stage performs localized recognition of text, formulas, and tables within detected regions, maintaining high visual fidelity while reducing error propagation. To address complex table structures, we propose a visual consistency-based reinforcement learning scheme that evaluates recognition quality via render-and-compare alignment, improving structural accuracy without manual annotations. Additionally, two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables containing embedded images and reconstruction of tables crossing pages or columns. Comprehensive experiments on OmniDocBench v1.5 demonstrate that MonkeyOCR v1.5 achieves state-of-the-art performance, outperforming PPOCR-VL and MinerU 2.5 while showing exceptional robustness in visually complex document scenarios. A trial link can be found at https://github.com/Yuliang-Liu/MonkeyOCR .