Search papers, labs, and topics across Lattice.
OvisOCR2 is a 0.8B end-to-end document parsing model that generates Markdown representations from document page images, effectively handling text, formulas, tables, and visual regions. The model leverages a novel data engine combining filtered real-document annotations with synthetic pages, and employs a training regimen that includes supervised fine-tuning and reinforcement learning. Achieving a state-of-the-art score of 96.58 on OmniDocBench v1.6, OvisOCR2 surpasses traditional pipeline methods, demonstrating significant advancements in end-to-end document parsing capabilities.
OvisOCR2 outperforms traditional pipeline methods, achieving a groundbreaking score of 96.58 in end-to-end document parsing.
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.
