---
title: "The olmOCR Project: Building Fully Open OCR using VLMs (2026)"
description: "The authors present olmOCR, an OCR system whose models, data, code and benchmark… 5.3 points. 36 references, cited by 1 paper here."
authors: ["Jake Poznanski", "Kyle Lo", "Luca Soldaini"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)"
source: "https://aclanthology.org/2026.acl-demo.62/"
doi: "10.18653/v1/2026.acl-demo.62"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/poznanski-2026-olmocr-project-building-fully-open/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/poznanski-2026-olmocr-project-building-fully-open/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/) / The olmOCR Project: Building Fully Open OCR using VLMs

# The olmOCR Project: Building Fully Open OCR using VLMs

**Authors:** [Jake Poznanski](https://md.research.elamur.ai/free/en/authors/jake-poznanski/), [Kyle Lo](https://md.research.elamur.ai/free/en/authors/kyle-lo/) and [Luca Soldaini](https://md.research.elamur.ai/free/en/authors/luca-soldaini/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-demo.62/) · [PDF](https://aclanthology.org/2026.acl-demo.62.pdf) · [DOI 10.18653/v1/2026.acl-demo.62](https://doi.org/10.18653/v1/2026.acl-demo.62) · [OpenAlex](https://openalex.org/W7166834452)

**Citations:** 1 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Turning PDFs into clean text is difficult because the format stores glyphs and coordinates rather than logical reading flow. Tables and formulas are especially hard, and extraction errors degrade LLM pretraining corpora. The authors present olmOCR, an OCR system whose models, data, code and benchmark are all openly released. They built it over two major versions guided by user feedback.

v1 distilled GPT-4.1 output into a 7B VLM through supervised fine-tuning. v2 adds RLVR, where the rewards are binary visual unit tests run on synthetic HTML-rendered pages. Those same tests make up olmOCR-Bench, which checks:
- text presence and absence,
- reading order,
- table cell positions,
- rendered math,
- output robustness.

The authors argue that edit distance misjudges outputs that are equivalent once rendered, which is why they use pass/fail tests instead. olmOCR scores 82.3% on olmOCR-Bench, the best result among similarly priced systems. It has been used to process over 100M PDFs for Olmo 3. The work shows that cheap, transparent OCR can compete with proprietary APIs. Its tests serve as both an evaluation tool and a training signal.

## Key points
- **Benchmark and training data:**
  - olmOCR-Bench has about 7,000 hand-verified binary tests over 1,400 documents, spanning seven document categories such as arXiv math, old scans and tables.
  - SFT data is olmOCR-mix-1025, roughly 250K English PDF pages; the abstract gives 260K.
  - RL data is olmOCR2-synthmix-1025, with 2,186 pages and 30,381 tests.
- **Base models:** Qwen2.5-VL-7B and Qwen-3VL-8B, each fine-tuned for one epoch.
- **Comparison with other systems:**
  - olmOCR costs about $165 per 10K pages and scores 82.3%.
  - Chandra scores slightly higher (83.1%) but costs about $4,000.
  - DeepSeek-OCR scores 75.7%.
  - olmOCR beats GPT-4.1 by 11.3 points while being more than 37× cheaper.
- **Engineering fixes without retraining:**
  - Having the model emit YAML rather than JSON reduced page retries from about 40% to about 1%.
  - Dynamic temperature and other tweaks helped lift scores from 68.2% (v1 0225) to 78.5% (v1 0825).
  - RLVR added 5.3 points, mainly on math and tables.
- **Deployment:**
  - The model runs in FP8 on vLLM at about 3,500 tokens/s on one H100.
  - It has processed over 100M PDFs, about 1T tokens, for Olmo 3 pretraining.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 275 works · 97,634 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works

## Cite

Cite as: Jake Poznanski, Kyle Lo and Luca Soldaini. 2026. The olmOCR Project: Building Fully Open OCR using VLMs. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{poznanski2026olmocr,
  title = {{The olmOCR Project: Building Fully Open OCR using VLMs}},
  author = {Jake Poznanski, Kyle Lo and Luca Soldaini},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-demo.62},
  url = {https://doi.org/10.18653/v1/2026.acl-demo.62}
}
```

- [← previous The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models](https://md.research.elamur.ai/free/en/papers/lohr-2026-hidden-bias-study-explicit-implicit/)
- [next → The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs Using Indian Riddles](https://md.research.elamur.ai/free/en/papers/m-2026-riddle-reflection-evaluating-reasoning-self/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/9/)

## References

36 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. [Qwen2.5-VL technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). arXiv [cs.CV].
2. Lukas Blecher, Guillem Cucurull, Thomas Scialom, and Robert Stojnic. 2023. Nougat: Neural optical understanding for academic documents. Preprint, arXiv:2308.13418. [find](https://scholar.google.com/scholar?q=Lukas+Blecher%2C+Guillem+Cucurull%2C+Thomas+Scialom%2C+and+Robert+Stojnic%2E+2023%2E+Nougat%3A+Neural+optical+understanding+for+academic+documents%2E+Preprint%2C+arXiv%3A2308%2E13418%2E)
3. Qian Chen, Xianyin Zhang, Lifan Guo, Feng Chen, and Chi Zhang. 2025. Dianjin-ocr-r1: Enhancing ocr capabilities via a reasoning-and-tool interleaved vision-language model. Preprint, arXiv:2508.13238. — [arXiv:2508.13238](https://arxiv.org/abs/2508.13238) [find](https://scholar.google.com/scholar?q=Qian+Chen%2C+Xianyin+Zhang%2C+Lifan+Guo%2C+Feng+Chen%2C+and+Chi+Zhang%2E+2025%2E+Dianjin%2Docr%2Dr1%3A+Enhancing+ocr+capabilities+via+a+reasoning%2Dand%2Dtool+interleaved+vision%2Dlanguage+model%2E+Preprint%2C+arXiv%3A2508%2E13238%2E+)
4. Cheng Cui, Ting Sun, Manhui Lin, Tingquan Gao, Yubo Zhang, Jiaxuan Liu, Xueqing Wang, Zelun Zhang, Changda Zhou, Hongen Liu, Yue Zhang, Wenyu Lv, Kui Huang, Yichao Zhang, Jing Zhang, Jun Zhang, Yi Liu, Dianhai Yu, and Yanjun Ma. 2025. Paddleocr 3.0 technical report. Preprint, arXiv:2507.05595. — [arXiv:2507.05595](https://arxiv.org/abs/2507.05595) [find](https://scholar.google.com/scholar?q=Cheng+Cui%2C+Ting+Sun%2C+Manhui+Lin%2C+Tingquan+Gao%2C+Yubo+Zhang%2C+Jiaxuan+Liu%2C+Xueqing+Wang%2C+Zelun+Zhang%2C+Changda+Zhou%2C+Hongen+Liu%2C+Yue+Zhang%2C+Wenyu+Lv%2C+Kui+Huang%2C+Yichao+Zhang%2C+Jing+Zhang%2C+Jun+Zhang%2C+Yi+Liu)
5. DeepSeek-AI. 2025. [Deepseek-ocr: Contexts optical compression](https://md.research.elamur.ai/free/en/papers/wei-2025-deepseek-ocr-contexts-optical/). Model available at: [https://huggingface.co/](https://huggingface.co/) deepseek-ai/DeepSeek-OCR. [↗](https://huggingface.co/)
6. Patrick Emond. 2025. Lingua-py: Natural language detection for python. Accessed: 2025-01-06. [find](https://scholar.google.com/scholar?q=Patrick+Emond%2E+2025%2E+Lingua%2Dpy%3A+Natural+language+detection+for+python%2E+Accessed%3A+2025%2D01%2D06%2E)
7. Zhentao He, Can Zhang, Ziheng Wu, Zhenghao Chen, Yufei Zhan, Yifan Li, Zhao Zhang, Xian Wang, and Minghui Qiu. 2025. Seeing is believing? mitigating ocr hallucinations in multimodal large language models. Preprint, arXiv:2506.20168. — [arXiv:2506.20168](https://arxiv.org/abs/2506.20168) [find](https://scholar.google.com/scholar?q=Zhentao+He%2C+Can+Zhang%2C+Ziheng+Wu%2C+Zhenghao+Chen%2C+Yufei+Zhan%2C+Yifan+Li%2C+Zhao+Zhang%2C+Xian+Wang%2C+and+Minghui+Qiu%2E+2025%2E+Seeing+is+believing%3F+mitigating+ocr+hallucinations+in+multimodal+large+language+mod)
8. Geewook Kim, Teakgyu Hong, Moonbin Yim, JeongYeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, and Seunghyun Park. 2021. [Ocr-free document understanding transformer](https://md.research.elamur.ai/free/en/papers/kim-2021-ocr-free-document-understanding-transformer/). In European Conference on Computer Vision.
9. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
10. Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Gadre, Hritik Bansal, Etash Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, and 40 others. 2024. [DataComp-L…](https://md.research.elamur.ai/free/en/papers/li-2024-datacomp-lm-search-next-generation/)
11. Kyle Lo, Joseph Chee Chang, Andrew Head, Jonathan Bragg, Amy X. Zhang, Cassidy Trier, Chloe Anastasiades, Tal August, Russell Authur, Danielle Bragg, Erin Bransom, Isabel Cachola, Stefan Candra, Yoganand Chandrasekhar, Yen-Sung Chen, Evie Yu-Yen Cheng, Yvonne Chou, Doug Downey, Rob Evans, and 36 oth… [find](https://scholar.google.com/scholar?q=Kyle+Lo%2C+Joseph+Chee+Chang%2C+Andrew+Head%2C+Jonathan+Bragg%2C+Amy+X%2E+Zhang%2C+Cassidy+Trier%2C+Chloe+Anastasiades%2C+Tal+August%2C+Russell+Authur%2C+Danielle+Bragg%2C+Erin+Bransom%2C+Isabel+Cachola%2C+Stefan+Candra%2C+Yogan)
12. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. Preprint, arXiv:1711.05101. [find](https://scholar.google.com/scholar?q=Ilya+Loshchilov+and+Frank+Hutter%2E+2019%2E+Decoupled+weight+decay+regularization%2E+Preprint%2C+arXiv%3A1711%2E05101%2E)
13. Souvik Mandal, Ashish Talewar, Siddhant Thakuria, Paras Ahuja, and Prathamesh Juvatkar. 2025. Nanonets-ocr2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging. [find](https://scholar.google.com/scholar?q=Souvik+Mandal%2C+Ashish+Talewar%2C+Siddhant+Thakuria%2C+Paras+Ahuja%2C+and+Prathamesh+Juvatkar%2E+2025%2E+Nanonets%2Docr2%3A+A+model+for+transforming+documents+into+structured+markdown+with+intelligent+content+recogn)
14. S Mori, C Y Suen, and K Yamamoto. 1992. Historical review of OCR research and development. Proceedings of the IEEE. Institute of Electrical and Electronics Engineers, 80(7):1029–1058. [find](https://scholar.google.com/scholar?q=S+Mori%2C+C+Y+Suen%2C+and+K+Yamamoto%2E+1992%2E+Historical+review+of+OCR+research+and+development%2E+Proceedings+of+the+IEEE%2E+Institute+of+Electrical+and+Electronics+Engineers%2C+80%287%29%3A1029%E2%80%931058%2E)
15. Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Yuanhong Zheng, Dongsheng Ma, and 42 others. 2025a. [Mineru2.5: A decoupled vision-language…](https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/)
16. Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, and 1 others. 2025b. Mineru2. 5: A decoupled vision-language model for efficient high-resolution document parsing. arXiv preprint arXiv:2509.22186. — [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://md.research.elamur.ai/free/en/papers/niu-2026-mineru2-5-decoupled-vision-language/)
17. Team Olmo, Allyson Ettinger, Amanda Bertsch, Bailey Kuehl, David Graham, David Heineman, Dirk Groeneveld, Faeze Brahman, Finbarr Timbers, Hamish Ivison, Jacob Morrison, Jake Poznanski, Kyle Lo, Luca Soldaini, Matt Jordan, Mayee Chen, Michael Noukhovitch, Nathan Lambert, Pete Walsh, and 49 others. 20… — [Olmo 3](https://md.research.elamur.ai/free/en/papers/ettinger-2025-olmo-3/)
18. Team OLMo, Pete Walsh, Luca Soldaini, Dirk Groeneveld, Kyle Lo, Shane Arora, Akshita Bhagia, Yuling Gu, Shengyi Huang, Matt Jordan, Nathan Lambert, Dustin Schwenk, Oyvind Tafjord, Taira Anderson, David Atkinson, Faeze Brahman, Christopher Clark, Pradeep Dasigi, Nouha Dziri, and 21 others. 2024. 2 OL… [find](https://scholar.google.com/scholar?q=Team+OLMo%2C+Pete+Walsh%2C+Luca+Soldaini%2C+Dirk+Groeneveld%2C+Kyle+Lo%2C+Shane+Arora%2C+Akshita+Bhagia%2C+Yuling+Gu%2C+Shengyi+Huang%2C+Matt+Jordan%2C+Nathan+Lambert%2C+Dustin+Schwenk%2C+Oyvind+Tafjord%2C+Taira+Anderson%2C+Davi)
19. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others.… — [GPT-4 Technical Report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/)
20. Linke Ouyang, Yuan Qu, Hongbin Zhou, Jiawei Zhu, Rui Zhang, Qunshu Lin, Bin Wang, Zhiyuan Zhao, Man Jiang, Xiaomeng Zhao, Jin Shi, Fan Wu, Pei Chu, Minghao Liu, Zhenxiang Li, Chao Xu, Bo Zhang, Botian Shi, Zhongying Tu, and Conghui He. 2024. Omnidocbench: Benchmarking diverse pdf document parsing wi… — [arXiv:2412.07626](https://arxiv.org/abs/2412.07626) [find](https://scholar.google.com/scholar?q=Linke+Ouyang%2C+Yuan+Qu%2C+Hongbin+Zhou%2C+Jiawei+Zhu%2C+Rui+Zhang%2C+Qunshu+Lin%2C+Bin+Wang%2C+Zhiyuan+Zhao%2C+Man+Jiang%2C+Xiaomeng+Zhao%2C+Jin+Shi%2C+Fan+Wu%2C+Pei+Chu%2C+Minghao+Liu%2C+Zhenxiang+Li%2C+Chao+Xu%2C+Bo+Zhang%2C+Botian)
21. Vik Paruchuri. 2025a. chandra: OCR model that handles complex tables, forms, handwriting with full layout. [https://github.com/](https://github.com/) datalab-to/chandra. GitHub repository. [↗](https://github.com/)
22. Vik Paruchuri. 2025b. Marker: Convert pdf to markdown + json quickly with high accuracy. Version 1.4.0. [find](https://scholar.google.com/scholar?q=Vik+Paruchuri%2E+2025b%2E+Marker%3A+Convert+pdf+to+markdown+%2B+json+quickly+with+high+accuracy%2E+Version+1%2E4%2E0%2E)
23. Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra-Aimée Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only. ArXiv, abs/2306.01… [find](https://scholar.google.com/scholar?q=Guilherme+Penedo%2C+Quentin+Malartic%2C+Daniel+Hesslow%2C+Ruxandra%2DAime%CC%81e+Cojocaru%2C+Alessandro+Cappelli%2C+Hamza+Alobeidli%2C+Baptiste+Pannier%2C+Ebtesam+Almazrouei%2C+and+Julien+Launay%2E+2023%2E+The+refinedweb+datase)
24. Jake Poznanski, Jon Borchardt, Jason Dunkelberger, Regan Huff, Daniel Lin, Aman Rangapur, Christopher Wilhelm, Kyle Lo, and Luca Soldaini. 2025a. [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://md.research.elamur.ai/free/en/papers/poznanski-2025-olmocr-unlocking-trillions-tokens-pdfs/). Preprint, arXiv:2502.18443.
25. Jake Poznanski, Luca Soldaini, and Kyle Lo. 2025b. olmOCR 2: Unit Test Rewards for Document OCR. Technical report, Allen Institute for AI. [find](https://scholar.google.com/scholar?q=Jake+Poznanski%2C+Luca+Soldaini%2C+and+Kyle+Lo%2E+2025b%2E+olmOCR+2%3A+Unit+Test+Rewards+for+Document+OCR%2E+Technical+report%2C+Allen+Institute+for+AI%2E)
26. RedNote HiLab. 2025. dots.ocr: Multilingual document layout parsing in a single vision-language model. Version 1.0, Released July 30, 2025. [find](https://scholar.google.com/scholar?q=RedNote+HiLab%2E+2025%2E+dots%2Eocr%3A+Multilingual+document+layout+parsing+in+a+single+vision%2Dlanguage+model%2E+Version+1%2E0%2C+Released+July+30%2C+2025%2E)
27. Bin Wang, Chao Xu, Xiaomeng Zhao, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Rui Xu, Kaiwen Liu, Yuan Qu, Fukai Shang, Bo Zhang, Liqun Wei, Zhihao Sui, Wei Li, Botian Shi, Yu Qiao, Dahua Lin, and Conghui He. 2024. Mineru: An open-source solution for precise document content extraction. Preprint, arXiv:2409… [find](https://scholar.google.com/scholar?q=Bin+Wang%2C+Chao+Xu%2C+Xiaomeng+Zhao%2C+Linke+Ouyang%2C+Fan+Wu%2C+Zhiyuan+Zhao%2C+Rui+Xu%2C+Kaiwen+Liu%2C+Yuan+Qu%2C+Fukai+Shang%2C+Bo+Zhang%2C+Liqun+Wei%2C+Zhihao+Sui%2C+Wei+Li%2C+Botian+Shi%2C+Yu+Qiao%2C+Dahua+Lin%2C+and+Conghui+He%2E)
28. Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, and 1 others. 2024. General ocr theory: Towards ocr-2.0 via a unified end-to-end model. arXiv preprint arXiv:2409.01704. — [arXiv:2409.01704](https://arxiv.org/abs/2409.01704) [find](https://scholar.google.com/scholar?q=Haoran+Wei%2C+Chenglong+Liu%2C+Jinyue+Chen%2C+Jia+Wang%2C+Lingyu+Kong%2C+Yanming+Xu%2C+Zheng+Ge%2C+Liang+Zhao%2C+Jianjian+Sun%2C+Yuang+Peng%2C+and+1+others%2E+2024%2E+General+ocr+theory%3A+Towards+ocr%2D2%2E0+via+a+unified+end%2Dto%2D)
29. Junyu Xiong, Yonghui Wang, Weichao Zhao, Chenyu Liu, Bing Yin, Wengang Zhou, and Houqiang Li. 2025. Docr1: Evidence page-guided grpo for multi-page document understanding. Preprint, arXiv:2508.07313. — [arXiv:2508.07313](https://arxiv.org/abs/2508.07313) [find](https://scholar.google.com/scholar?q=Junyu+Xiong%2C+Yonghui+Wang%2C+Weichao+Zhao%2C+Chenyu+Liu%2C+Bing+Yin%2C+Wengang+Zhou%2C+and+Houqiang+Li%2E+2025%2E+Docr1%3A+Evidence+page%2Dguided+grpo+for+multi%2Dpage+document+understanding%2E+Preprint%2C+arXiv%3A2508%2E07313%2E+)
30. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
31. Zhiyuan Zhao, Hengrui Kang, Bin Wang, and Conghui He. 2024. Doclayout-yolo: Enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. arXiv preprint arXiv:2410.12628. — [arXiv:2410.12628](https://arxiv.org/abs/2410.12628) [find](https://scholar.google.com/scholar?q=Zhiyuan+Zhao%2C+Hengrui+Kang%2C+Bin+Wang%2C+and+Conghui+He%2E+2024%2E+Doclayout%2Dyolo%3A+Enhancing+document+layout+analysis+through+diverse+synthetic+data+and+global%2Dto%2Dlocal+adaptive+perception%2E+arXiv+preprint+ar)
32. Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, and Junyang Lin. 2025. [Group sequence policy optimization](https://md.research.elamur.ai/free/en/papers/zheng-2025-group-sequence-policy-optimization/). Preprint, arXiv:2507.18071.
33. Ray W Smith. 2013. History of the tesseract OCR engine: what worked and what didn’t. In Document Recognition and Retrieval XX, volume 8658, page 865802. SPIE. [find](https://scholar.google.com/scholar?q=Ray+W+Smith%2E+2013%2E+History+of+the+tesseract+OCR+engine%3A+what+worked+and+what+didn%E2%80%99t%2E+In+Document+Recognition+and+Retrieval+XX%2C+volume+8658%2C+page+865802%2E+SPIE%2E)
34. Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallouédec. 2020. Trl: Transformer reinforcement learning. [https://github.com/](https://github.com/) huggingface/trl. [↗](https://github.com/)
35. Baode Wang, Biao Wu, Weizhen Li, Meng Fang, Yanjie Liang, Zuming Huang, Haozhe Wang, Jun Huang, Ling Chen, Wei Chu, and Yuan Qi. 2025a. Infinity parser: Layout aware reinforcement learning for scanned document parsing. Preprint, arXiv:2506.03197. — [arXiv:2506.03197](https://arxiv.org/abs/2506.03197) [find](https://scholar.google.com/scholar?q=Baode+Wang%2C+Biao+Wu%2C+Weizhen+Li%2C+Meng+Fang%2C+Yanjie+Liang%2C+Zuming+Huang%2C+Haozhe+Wang%2C+Jun+Huang%2C+Ling+Chen%2C+Wei+Chu%2C+and+Yuan+Qi%2E+2025a%2E+Infinity+parser%3A+Layout+aware+reinforcement+learning+for+scanned)
36. Bin Wang, Fan Wu, Linke Ouyang, Zhuangcheng Gu, Rui Zhang, Renqiu Xia, Bo Zhang, and Conghui He. 2025b. Image over text: Transforming formula recognition evaluation with character detection matching. Preprint, arXiv:2409.03643. — [arXiv:2409.03643](https://arxiv.org/abs/2409.03643) [find](https://scholar.google.com/scholar?q=Bin+Wang%2C+Fan+Wu%2C+Linke+Ouyang%2C+Zhuangcheng+Gu%2C+Rui+Zhang%2C+Renqiu+Xia%2C+Bo+Zhang%2C+and+Conghui+He%2E+2025b%2E+Image+over+text%3A+Transforming+formula+recognition+evaluation+with+character+detection+matching%2E+)

*Updated 31 October 2026*