OvisOCR3 Technical Report
We introduce OvisOCR3, a 0.8B model for a broad range of OCR-related tasks. OvisOCR3 unifies document parsing, general OCR, key information extraction (KIE), document figure captioning, and cross-page table reconstruction in a single model. We train the model on real and synthetic data through continued pretraining and use domain-balanced mid-training to balance supervision across tasks with different data volumes and response lengths. Multi-teacher on-policy distillation transfers expertise from five domain-specific 4B teachers into the shared model, followed by mixed-task reinforcement learning with domain-specific rewards. We compare OvisOCR3 with general-purpose vision-language models...
| Authors | Yu Xia, Yinglun Li, Yuhui Chen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 20 October 2026 |
| Last updated at source | 20 October 2026 |
Popularity, last 14 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- ATH-MaaS/OvisOCR3Model · cited by
Models and datasets referencing this paper
- ATH-MaaS/OvisOCR3Model
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 9 November 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.