Abstract
Optical Character Recognition (OCR) for mathematical formula is essential for the intelligent analysis of scientific literature. However, both task-specific and general vision-language models often struggle to handle the structural diversity, complexity, and real-world variability inherent in mathematical content. In this work, we present DocTron-Formula, a unified framework built upon general vision-language models, thereby eliminating the need for specialized architectures. Furthermore, we introduce CSFormula, a large-scale and challenging dataset that encompasses multidisciplinary and structurally complex formulas at the line, paragraph, and page levels. Through straightforward supervised fine-tuning, our approach achieves state-of-the-art performance across a variety of styles, scientific domains, and complex layouts. Experimental results demonstrate that our method not only surpasses specialized models in terms of accuracy and robustness, but also establishes a new paradigm for the automated understanding of complex scientific documents.
Abstract (translated)
光学字符识别（OCR）对于数学公式的智能分析至关重要，这对于科学文献的智能分析尤为重要。然而，无论是特定任务的模型还是通用视觉-语言模型，在处理数学内容固有的结构多样性、复杂性和现实世界变异性方面往往面临挑战。在本研究中，我们提出了DocTron-Formula，这是一个基于通用视觉-语言模型构建的统一框架，从而消除了对专门架构的需求。此外，我们引入了CSFormula，这是包含多学科和结构复杂的公式的大规模且具有挑战性的数据集，这些公式涵盖了行、段落及页面级别。通过简单的监督微调，我们的方法在各种风格、科学领域以及复杂布局方面均实现了最先进的性能。实验结果表明，我们的方法不仅在准确性和鲁棒性上超越了专门模型，并且为自动理解复杂的科学文档建立了一个新的范式。
URL
https://arxiv.org/abs/2508.00311
