1.2B参数模型高效解析高分辨率文档，精度与速度兼得
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
- 分两阶段解析：先粗略分析布局，再精准识别内容
- 在多个基准上超越现有模型，计算开销更低
- 适合需要高精度文档处理的工业场景
我们提出MinerU2.5，一个1.2B参数的文档解析视觉语言模型，在保持卓越计算效率的同时达到顶尖识别精度。采用自粗到细的两阶段解析策略，将全局布局分析与局部内容识别解耦。第一阶段在下采样图像上高效进行布局分析，避免高分辨率输入带来的计算负担；第二阶段基于全局布局，对原始图像中提取的原生分辨率图像块进行针对性内容识别，保留密集文本、复杂公式和表格的细微细节。为此，我们构建了全面的数据引擎，生成多样且大规模的训练数据集，用于预训练与微调。最终，MinerU2.5在多个基准测试中表现优异，超越通用及领域专用模型，在各类识别任务中均达先进水平，同时显著降低计算开销。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。