| title | PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence |
|---|---|
| authors | GuangJian Team, Kaili Huang, Yongshuo Zhang, Bingtao Fu, Changjiang Jiang, Chenfan Qu, Chenfeng Zhang, Fangming Cui, Gaoyang Zhang, Jiangwei Xie, Jianshu Li, Jing Huang, Jingwen Bai, Mingqi Fang, Tao Fang, Weihong Zhang, Wenbo Du, Xiongfei Bai, Xuekang Zhu, Yinan Xia, Zhenming Wang, Jian Liu, Jingjing Liu, Xiang Qi, Weiqiang Wang |
| date | 2026-09-29 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.37712 |
| affiliation | inclusionAI |
| upvotes | 31 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over textual information in complex visual environments. However, existing OCR systems often excel at only some tasks and struggle to balance recognition, parsing, and reasoning across scenarios. In this report, we present PolyOCR, a family of unified OCR foundation models of varying scales. PolyOCR combines a shared instruction-following framework with a large-scale data engine that converts heterogeneous visual resources into quality-verified OCR supervision. We introduce Competence-Guided Policy Optimization, which combines verifier-based Group Relative Policy Optimization with on-policy distillation through sample-wise routing based on teacher reliability and the teacher--student competence gap. We also introduce OCRBench v2.1, our revision of OCRBench v2 with manually verified annotation corrections and task-aligned scoring metrics. Extensive experiments across OCRBench v2.1, CC-OCR, in-house KIE Benchmark, OmniDocBench v1.6 and MDPBench demonstrate that PolyOCR achieves state-of-the-art or highly competitive performance. |
cite
@misc{team2026polyocr,
title={PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence},
author={GuangJian Team and Kaili Huang and Yongshuo Zhang and Bingtao Fu and Changjiang Jiang and Chenfan Qu and Chenfeng Zhang and Fangming Cui and Gaoyang Zhang and Jiangwei Xie and Jianshu Li and Jing Huang and Jingwen Bai and Mingqi Fang and Tao Fang and Weihong Zhang and Wenbo Du and Xiongfei Bai and Xuekang Zhu and Yinan Xia and Zhenming Wang and Jian Liu and Jingjing Liu and Xiang Qi and Weiqiang Wang},
year={2026},
eprint={2609.37712},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.37712}
}