一键将文档图像转为干净Markdown，无需复杂流程。
ABot-OCR Technical Report
- 端到端模型直接输出结构化Markdown，省去传统繁琐步骤。
- 在OmniDocBench上达93.30分，超越所有同类系统。
- 支持十种语言，通用性强，适合多场景文档处理。
我们提出ABot-OCR，一种端到端的视觉语言模型，可直接将页面图像转为干净的Markdown，仅需一次前向传播。该方法彻底消除对脆弱模块编排的依赖。为提升解析准确性，我们构建了大规模、结构一致的专用数据引擎。此外，提出解耦异构文档优化（Decoupled Heterogeneous Document Optimization），一种结构约束的强化学习方法，显著提升文本准确率并严格保证标记语法正确性，超越监督微调效果。大量评估显示，其性能优异：在OmniDocBench v1.5和v1.6基准上分别取得92.81和93.30的得分，大幅缩小与强基准流水线系统的差距。跨十种不同语言的全面文本识别进一步验证了ABot-OCR的鲁棒泛化能力。
原文摘要 · Abstract (English)
We introduce ABot-OCR, an end-to-end vision-language model that transcribes a page image directly into clean Markdown in a single forward pass. By doing so, our approach completely eliminates the need for brittle modular orchestration. To maximize parsing fidelity, we develop a dedicated data engine to provide large-scale, structurally consistent supervision. Furthermore, we propose Decoupled Heterogeneous Document Optimization, a structure-constrained reinforcement learning method that sharpens textual accuracy and strictly enforces markup well-formedness beyond supervised fine-tuning alone. Extensive evaluations demonstrate the superior performance of our framework. On the OmniDocBench v1.5 and v1.6 benchmarks, ABot-OCR achieves state-of-the-art scores of 92.81 and 93.30 among all end-to-end systems, substantially narrowing the performance gap relative to strong pipeline baselines. Finally, comprehensive multilingual text recognition across ten diverse languages further confirms the robust generalizability of ABot-OCR.
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。