Metraipolis › archive › dc_06461dd5fc2b
OCRia-1 Technical Report — arXiv:2611.00092
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00092
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:40:32.556Z
- SHA-256 of the archived text
a4bea92ee71042453713f5822255ace0be2b1ab960a12c06f2c9fb182a217f83- Stable URL of this page
https://metraipolis.com/documento/dc_06461dd5fc2b
How to cite
OCRia-1 Technical Report — arXiv:2611.00092 — arXiv (en), https://arxiv.org/abs/2611.00092 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_06461dd5fc2b (Metraipolis archive dc_06461dd5fc2b, sha256 a4bea92ee71042453713f5822255ace0be2b1ab960a12c06f2c9fb182a217f83)
BibTeX
@misc{dc06461dd5fc2b,
title = {OCRia-1 Technical Report — arXiv:2611.00092},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00092},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_06461dd5fc2b; sha256 a4bea92ee71042453713f5822255ace0be2b1ab960a12c06f2c9fb182a217f83},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00092. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce OCRia-1, a 4B vision-language model (VLM) for document parsing that excels at preserving table structure, extracting chart data and retaining text formatting. OCRia-1 handles content that has traditionally been challenging in document parsing: merged cells and spanning headers, tables with thousands of cells, chart data, and meaningful text formatting such as bold, italics, subscripts and superscripts, preserving details needed for business-critical document analysis. At the time of this report, it achieves the highest scores on tables, charts and text formatting among the systems evaluated, including a 35B model and Mistral OCR 4.1. Its mean ParseBench score over the four dimensions we evaluate is 0.87, against 0.75 for the next-best system. We emphasize data quality and reward design in training OCRia-1. Synthetic pages provide exact ground truth for long tables and rich formatting, while real pages are transcribed using a pipeline grounded in the PDF text layer. We attribute OCRia-1's performance primarily to careful data curation that prioritizes quality and diversity over quantity. Dimension-specific rewards evaluate table reconstruction, chart-data extraction and text-formatting fidelity. We train the model on the curated data using supervised fine-tuning (SFT), then refine it through reinforcement learning with verifiable rewards (RLVR). To our knowledge, OCRia-1 is the fastest published document-parsing VLM in its class, decoding at about 4,700 tokens per second with a single request on one B200 GPU, about nine times faster than the base model on stock vLLM. This is achieved through a block-diffusion speculator, quantization and custom kernels. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.00092 — 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 2026-11-03T11:06:37.402Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).