Metraipolis › archive › dc_af290fa496c6
Xiaomi-OCR-0 Technical Report — arXiv:2609.36136
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36136
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T18:38:01.101Z
- SHA-256 of the archived text
2f982cae2a2e94993095073506e5afa823b66333fbe8f857379680d570d3fdd8- Stable URL of this page
https://metraipolis.com/documento/dc_af290fa496c6
How to cite
Xiaomi-OCR-0 Technical Report — arXiv:2609.36136 — arXiv (en), https://arxiv.org/abs/2609.36136 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af290fa496c6 (Metraipolis archive dc_af290fa496c6, sha256 2f982cae2a2e94993095073506e5afa823b66333fbe8f857379680d570d3fdd8)
BibTeX
@misc{dcaf290fa496c6,
title = {Xiaomi-OCR-0 Technical Report — arXiv:2609.36136},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36136},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af290fa496c6; sha256 2f982cae2a2e94993095073506e5afa823b66333fbe8f857379680d570d3fdd8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36136. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.36136 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T18:04:24.677Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).