Abstract
Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on visual-text reconstruction. We introduce Xiaomi-OCR-0, a unified 0.8B model for document parsing and OCR-centric understanding. We build an approximately 170M-sample OCR-centric corpus using an automated data engine that combines expert consensus, render-based verification, and targeted synthesis. Starting from Qwen3.5-0.8B, our progressive training recipe combines Q-Mask-based text anchoring, continued pretraining, and mixed-task reinforcement learning (Mix-RL). Xiaomi-OCR-0 achieves 95.24 on Real5-OmniDocBench, 96.83 on OmniDocBench v1.6, and 87.94 on Wild-OmniDocBench, while reaching an average score of 83.2 across five OCR-oriented VQA benchmarks. Ablations further show that, with sufficient parsing training, OCR-centric understanding supervision provides additional gains for document parsing. Homepage: https://huggingface.co/spaces/SeerRay-Lab/Xiaomi-OCR-0.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Chen, X., Du, A., Feng, F., Fu, P., Luan, J., Xu, L., Zhang, S., Li, H., Qu, H., & Tan, C. (2026). Xiaomi-OCR-0 Technical Report. https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report
MLA 9
Chen, Xin, et al. "Xiaomi-OCR-0 Technical Report." https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report.
Chicago (author–date)
Chen, Xin, Anan Du, Feng Feng, Pei Fu, Jian Luan, Longwei Xu, Shaojie Zhang, Hang Li, Heng Qu, and Cheng Tan. 2026. "Xiaomi-OCR-0 Technical Report." https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report.
Harvard
Chen, X., Du, A., Feng, F., Fu, P., Luan, J., Xu, L., Zhang, S., Li, H., Qu, H. and Tan, C. (2026) 'Xiaomi-OCR-0 Technical Report', Available at: https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report.
Vancouver
Chen X, Du A, Feng F, Fu P, Luan J, Xu L, et al. Xiaomi-OCR-0 Technical Report. https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report
IEEE
X. Chen, A. Du, F. Feng, P. Fu, J. Luan, L. Xu, S. Zhang, H. Li, H. Qu, and C. Tan, "Xiaomi-OCR-0 Technical Report," https://omanscience.com/en/articles/xiaomi-ocr-0-technical-report.