OvisOCR2 技术报告

摘要

我们推出了OvisOCR2，一个0.8B参数量的文档解析模型。OvisOCR2被设计为端到端解析器：给定文档页面图像，它能够按照自然阅读顺序生成涵盖文本、公式、表格和视觉区域的Markdown表示。我们构建了一个数据引擎，融合了经过筛选的真实文档标注和合成页面——这些页面的渲染图像与Markdown目标均源自同一HTML源。训练方案包括监督微调、在4B分支上采用多组件奖励设计的强化学习、在线策略蒸馏至0.8B模型，以及模型融合。在OmniDocBench v1.6上，OvisOCR2取得了96.58的整体最佳分数，将端到端模型置于此前由流水线方法主导的排行榜首位，凸显了端到端文档解析的潜力。在PureDocBench上，OvisOCR2同样以75.06的最高Avg3分数表现优异。除这两个公开基准外，我们还在内部基准上评估了OvisOCR2，该基准旨在覆盖更广泛的长尾与高挑战性场景。OvisOCR2在所比较的方法中取得了最佳整体性能，进一步证实了其泛化能力与鲁棒性。OvisOCR2可通过https://huggingface.co/ATH-MaaS/OvisOCR2获取。

English

We introduce OvisOCR2, a 0.8B document parsing model. OvisOCR2 is designed as an end-to-end parser: given a document page image, it generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions. We build a data engine that combines filtered real-document annotations with synthetic pages whose rendered images and Markdown targets are derived from the same HTML source. The training recipe includes supervised fine-tuning, reinforcement learning on a 4B branch with a multi-component reward design, on-policy distillation into the 0.8B model, and model fusion. On OmniDocBench v1.6, OvisOCR2 achieves a state-of-the-art overall score of 96.58, placing an end-to-end model at the top of this leaderboard previously dominated by pipeline methods and highlighting the potential of end-to-end document parsing. On PureDocBench, OvisOCR2 also achieves the highest Avg3 score of 75.06. Beyond these two public benchmarks, we evaluate OvisOCR2 on an in-house benchmark designed to cover a broader set of long-tail and challenging scenarios. OvisOCR2 obtains the best overall performance among the compared methods, providing further evidence of its generalization and robustness. OvisOCR2 is available at https://huggingface.co/ATH-MaaS/OvisOCR2.

OvisOCR2 技术报告

OvisOCR2 Technical Report

摘要

Support