AI Insight
OvisOCR2 is a compact 0.8 billion parameter model that converts document page images directly into Markdown format, capturing text, formulas, tables, and visual regions in natural reading order. The model was trained using a combination of real document annotations and synthetic data, employing supervised fine-tuning, reinforcement learning on a larger 4B model, and knowledge distillation. It achieved state-of-the-art performance on OmniDocBench v1.6 with a score of 96.58 and the highest score of 75.06 on PureDocBench, surpassing traditional pipeline-based document parsing methods.
Why it matters
This end-to-end approach simplifies document digitization workflows by eliminating the need for multi-stage processing pipelines, potentially making document parsing more efficient and accessible. The model's strong performance on challenging scenarios suggests practical applications in automated document processing, accessibility tools, and knowledge extraction from scientific and business documents.
Understand the Science
arXiv:2607.13639v1 Announce Type: cross
Abstract: 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.
Source: OvisOCR2 Technical Report