---
title: "SCAN — paper by Ueda et al. (2026) — summary and ideas"
description: "The authors define a new task, semantic document layout analysis, and build SCAN to solve it. 35 references."
authors: ["Nobuhiro Ueda", "Yuyang Dong", "Krisztián Boros", "Daiki Ito", "Takuya Sera", "Masafumi Oyamada"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.82/"
doi: "10.18653/v1/2026.findings-eacl.82"
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/ueda-2026-scan-semantic-document-layout-analysis/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/ueda-2026-scan-semantic-document-layout-analysis/)

[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/17/) / SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation

# SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation

**Authors:** Nobuhiro Ueda, [Yuyang Dong](https://md.research.elamur.ai/free/en/authors/yuyang-dong/), Krisztián Boros, Daiki Ito, Takuya Sera and [Masafumi Oyamada](https://md.research.elamur.ai/free/en/authors/masafumi-oyamada/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/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.findings-eacl.82/) · [PDF](https://aclanthology.org/2026.findings-eacl.82.pdf) · [DOI 10.18653/v1/2026.findings-eacl.82](https://doi.org/10.18653/v1/2026.findings-eacl.82) · [OpenAlex](https://openalex.org/W7140135942)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
RAG systems over visually rich documents such as reports, manuals and flyers increasingly depend on VLMs. These models either transcribe page regions into text (textual RAG) or read page images directly (visual RAG). Giving a VLM an entire dense page works poorly. Conventional layout analysers like DocLayout-YOLO go the other way and split pages into tiny elements, which loses context. The authors define a new task, semantic document layout analysis, and build SCAN to solve it. SCAN divides a page into a few rectangular regions, each devoted to one subtopic, plus "global boxes" for page-level metadata such as title, header, footer, date and author. They annotated 24,577 Japanese pages from CCpdf, selected to cover diverse document clusters, and fine-tuned object detectors (YOLO11-X, RT-DETR-X) with RAG-oriented post-processing. Across three English and Japanese benchmarks, SCAN improved end-to-end textual RAG by 2.7–9.4 points and visual RAG by 5.6–10.4 points. It outperformed fine-grained layout tools and commercial parsers while lowering VLM processing time. Ablations attribute the gains to coarse chunk granularity rather than to model capacity or data size.

## Key points
- **Dataset:** 24,577 pages from the Japanese part of CCpdf (22,577 train / 1,000 validation / 1,000 test), annotated by six professional annotators.
  - The pages contain 123,151 boxes, about 5 per page, of which about 3.1 are semantic boxes.
  - Pages were sampled via agglomerative clustering on MiniCPM Visual Embedding vectors.
- **Box classes:** six categories, namely the semantic box plus global boxes covering the author, the date, the page title, the header and the footer.
  - The task is framed as multi-class object detection.
  - The RT-DETR-X variant performed best.
- **Granularity on 100 OHR-Bench pages:**
  - SCAN RT-DETR yields about 5.2 chunks per page, compared with 9.9–17.4 for DiT, DocLayout-YOLO and Beehive.
  - It scored 33.8 on textual RAG and 75.8 on visual RAG, versus 31.1 and 70.2 without chunking.
- **Data efficiency:** SCAN YOLO uses the same architecture as DocLayout-YOLO but about 23k rather than 80k annotations, and still clearly outperforms it.
- **Efficiency and limitations:**
  - Processing chunks shortens VLM inputs from about 1,320 to 781 tokens per request, which reduces total processing time.
  - The model cannot handle topics split across non-rectangular areas.
  - It was trained mainly on Japanese data.

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

📚 Shelves (6): [🖥️ 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 · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 473 works

## Cite

Cite as: Nobuhiro Ueda, Yuyang Dong, Krisztián Boros, Daiki Ito, Takuya Sera and Masafumi Oyamada. 2026. SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{ueda2026scan,
  title = {{SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation}},
  author = {Nobuhiro Ueda, Yuyang Dong, Krisztián Boros, Daiki Ito, Takuya Sera and Masafumi Oyamada},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.82},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.82}
}
```

- [← previous Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models](https://md.research.elamur.ai/free/en/papers/samadi-2026-scaling-test-time-compute-achieve/)
- [next → SCAN: Structured Capability Assessment and Navigation for LLMs](https://md.research.elamur.ai/free/en/papers/wang-2026-scan-structured-capability-assessment-navigation/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/17/)

## References

35 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Allganize.ai. 2024. Allganize rag leaderboard. [https://huggingface.co/datasets/allganize/](https://huggingface.co/datasets/allganize/) RAG-Evaluation-Dataset-JA. [↗](https://huggingface.co/datasets/allganize/)
2. Christoph Auer, Maksym Lysak, Ahmed Nassar, Michele Dolfi, Nikolaos Livathinos, Panos Vagenas, Cesar Berrospi Ramis, Matteo Omenetti, Fabian Lindlbauer, Kasper Dinkla, Lokesh Mishra, Yusik Kim, Shubham Gupta, Rafael Teixeira de Lima, Valery Weber, Lucas Morin, Ingmar Meijer, Viktor Kuropiatnyk, and… — [arXiv:2408.09869](https://arxiv.org/abs/2408.09869) [find](https://scholar.google.com/scholar?q=Christoph+Auer%2C+Maksym+Lysak%2C+Ahmed+Nassar%2C+Michele+Dolfi%2C+Nikolaos+Livathinos%2C+Panos+Vagenas%2C+Cesar+Berrospi+Ramis%2C+Matteo+Omenetti%2C+Fabian+Lindlbauer%2C+Kasper+Dinkla%2C+Lokesh+Mishra%2C+Yusik+Kim%2C+Shubha)
3. Shuai Bai, Yuxuan Cai, Ruizhe Chen, Keqin Chen, Xionghui Chen, Zesen Cheng, Lianghao Deng, Wei Ding, Chang Gao, Chunjiang Ge, Wenbin Ge, Zhifang Guo, Qidong Huang, Jie Huang, Fei Huang, Binyuan Hui, Shutong Jiang, Zhaohai Li, Mingsheng Li, Mei Li, Kaixin Li, Zicheng Lin, Junyang Lin, Xuejing Liu, Ji… — [Qwen3-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen3-vl-technical-report/)
4. 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, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Ha… — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
5. Lukas Blecher, Guillem Cucurull, Thomas Scialom, and Robert Stojnic. 2024. Nougat: Neural optical understanding for academic documents. In Proceedings of the Twelfth International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Lukas+Blecher%2C+Guillem+Cucurull%2C+Thomas+Scialom%2C+and+Robert+Stojnic%2E+2024%2E+Nougat%3A+Neural+optical+understanding+for+academic+documents%2E+In+Proceedings+of+the+Twelfth+International+Conference+on+Learni)
6. Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alex-ander Kirillov, and Sergey Zagoruyko. 2020. [End-to-end object detection with transformers](https://md.research.elamur.ai/free/en/papers/carion-2020-end-end-object-detection-transformers/). In Proceedings of the European Conference on Computer Vision (ECCV), pages 213–229. Springer.
7. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024a. [M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). In Findings of the Association for Computational Linguistics: ACL 2024, pages 2318–2335, Ban…
8. Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, et al. 2024b. [Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks](https://md.research.elamur.ai/free/en/papers/chen-2023-internvl-scaling-up-vision/). In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern…
9. Datalab. 2024. Marker. VikParuchuri/marker. [https://github.com/](https://github.com/) [↗](https://github.com/)
10. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. [A survey on rag meeting llms: Towards retrieval-augmented large language models](https://md.research.elamur.ai/free/en/papers/fan-2024-survey-rag-meeting-llms-towards/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, pages 6491–65…
11. Manuel Faysse, Hugues Sibille, Tony Wu, Bilel Omrani, Gautier Viaud, Céline Hudelot, and Pierre Colombo. 2024. Colpali: Efficient document retrieval with vision language models. Preprint, arXiv:2407.01449. [find](https://scholar.google.com/scholar?q=Manuel+Faysse%2C+Hugues+Sibille%2C+Tony+Wu%2C+Bilel+Omrani%2C+Gautier+Viaud%2C+C%C3%A9line+Hudelot%2C+and+Pierre+Colombo%2E+2024%2E+Colpali%3A+Efficient+document+retrieval+with+vision+language+models%2E+Preprint%2C+arXiv%3A2407%2E0)
12. Ling Fu, Biao Yang, Zhebin Kuang, Jiajun Song, Yuzhe Li, Linghao Zhu, Qidi Luo, Xinyu Wang, Hao Lu, Mingxin Huang, Zhang Li, Guozhi Tang, Bin Shan, Chunhui Lin, Qi Liu, Binghong Wu, Hao Feng, Hao Liu, Can Huang, Jingqun Tang, Wei Chen, Lianwen Jin, Yuliang Liu, and Xiang Bai. 2024. Ocrbench v2: An i… — [arXiv:2501.00321](https://arxiv.org/abs/2501.00321) [find](https://scholar.google.com/scholar?q=Ling+Fu%2C+Biao+Yang%2C+Zhebin+Kuang%2C+Jiajun+Song%2C+Yuzhe+Li%2C+Linghao+Zhu%2C+Qidi+Luo%2C+Xinyu+Wang%2C+Hao+Lu%2C+Mingxin+Huang%2C+Zhang+Li%2C+Guozhi+Tang%2C+Bin+Shan%2C+Chunhui+Lin%2C+Qi+Liu%2C+Binghong+Wu%2C+Hao+Feng%2C+Hao+Liu%2C)
13. Yunfan Gao, Yun Xiong, Xinyu Gao, Kangxiang Jia, Jinliu Pan, Yuxi Bi, Yi Dai, Jiawei Sun, Meng Wang, and Haofen Wang. 2024. [Retrieval-augmented generation for large language models: A survey](https://md.research.elamur.ai/free/en/papers/gao-2023-retrieval-augmented-generation-large-language/). Preprint, arXiv:2312.10997.
14. Multimedia, MM ’22, pages 3530–3539, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Multimedia%2C+MM+%E2%80%9922%2C+pages+3530%E2%80%933539%2C+New+York%2C+NY%2C+USA%2E+Association+for+Computing+Machinery%2E)
15. Minghao Li, Yiheng Xu, Lei Cui, Shaohan Huang, Furu Wei, Zhoujun Li, and Ming Zhou. 2020. Docbank: A benchmark dataset for document layout analysis. Preprint, arXiv:2006.01038. [find](https://scholar.google.com/scholar?q=Minghao+Li%2C+Yiheng+Xu%2C+Lei+Cui%2C+Shaohan+Huang%2C+Furu+Wei%2C+Zhoujun+Li%2C+and+Ming+Zhou%2E+2020%2E+Docbank%3A+A+benchmark+dataset+for+document+layout+analysis%2E+Preprint%2C+arXiv%3A2006%2E01038%2E)
16. LlamaParse.AI. 2025. Llamaparse: Transform unstructured data into llm optimized formats. [https://www.llamaindex.ai/llamaparse](https://www.llamaindex.ai/llamaparse). microsoft. 2025. Azure ai document intelligence. https://azure.microsoft. com/en-us/products/ai-services/ ai-document-intelligence. [↗](https://www.llamaindex.ai/llamaparse)
17. Mor Shpigel Nacson, Aviad Aberdam, Roy Ganz, Elad Ben Avraham, Alona Golts, Yair Kittenplon, Shai Mazor, and Ron Litman. 2024. Docvlm: Make your vlm an efficient reader. Preprint, arXiv:2412.08746. — [arXiv:2412.08746](https://arxiv.org/abs/2412.08746) [find](https://scholar.google.com/scholar?q=Mor+Shpigel+Nacson%2C+Aviad+Aberdam%2C+Roy+Ganz%2C+Elad+Ben+Avraham%2C+Alona+Golts%2C+Yair+Kittenplon%2C+Shai+Mazor%2C+and+Ron+Litman%2E+2024%2E+Docvlm%3A+Make+your+vlm+an+efficient+reader%2E+Preprint%2C+arXiv%3A2412%2E08746%2E+%E2%80%94+)
18. Birgit Pfitzmann, Christoph Auer, Michele Dolfi, Ahmed S Nassar, and Peter W J Staar. 2022. Doclaynet: A large human-annotated dataset for document-layout analysis. [find](https://scholar.google.com/scholar?q=Birgit+Pfitzmann%2C+Christoph+Auer%2C+Michele+Dolfi%2C+Ahmed+S+Nassar%2C+and+Peter+W+J+Staar%2E+2022%2E+Doclaynet%3A+A+large+human%2Dannotated+dataset+for+document%2Dlayout+analysis%2E)
19. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, Saizhuo Wang, Kun Zhang, Yuanzhuo Wang, Wen Gao, Lionel Ni, and Jian Guo. 2025. A survey on llm-as-a-judge. Preprint, arXiv:2411.15594. [find](https://scholar.google.com/scholar?q=Jiawei+Gu%2C+Xuhui+Jiang%2C+Zhichao+Shi%2C+Hexiang+Tan%2C+Xuehao+Zhai%2C+Chengjin+Xu%2C+Wei+Li%2C+Yinghan+Shen%2C+Shengjie+Ma%2C+Honghao+Liu%2C+Saizhuo+Wang%2C+Kun+Zhang%2C+Yuanzhuo+Wang%2C+Wen+Gao%2C+Lionel+Ni%2C+and+Jian+Guo%2E+20)
20. Jake Poznanski, Jon Borchardt, Jason Dunkelberger, Regan Huff, Daniel Lin, Aman Rangapur, Christopher Wilhelm, Kyle Lo, and Luca Soldaini. 2025. [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.
21. Yupan Huang, Tengchao Lv, Lei Cui, Yutong Lu, and Furu Wei. 2022. [Layoutlmv3: Pre-training for document ai with unified text and image masking](https://md.research.elamur.ai/free/en/papers/huang-2022-layoutlmv3-pre-training-document-ai/). In Proceedings of the 30th ACM International Conference on Multimedia, MM ’22, pages 4083–4091, New York, NY, USA. Association for Computing Machinery.
22. Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pages 779–788. [find](https://scholar.google.com/scholar?q=Joseph+Redmon%2C+Santosh+Divvala%2C+Ross+Girshick%2C+and+Ali+Farhadi%2E+2016%2E+You+only+look+once%3A+Unified%2C+real%2Dtime+object+detection%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+reco)
23. Rahima Khanam and Muhammad Hussain. 2024. Yolov11: An overview of the key architectural enhancements. Preprint, arXiv:2410.17725. — [arXiv:2410.17725](https://arxiv.org/abs/2410.17725) [find](https://scholar.google.com/scholar?q=Rahima+Khanam+and+Muhammad+Hussain%2E+2024%2E+Yolov11%3A+An+overview+of+the+key+architectural+enhancements%2E+Preprint%2C+arXiv%3A2410%2E17725%2E+%E2%80%94+%5BarXiv%3A2410%2E17725%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2410%2E17725%29)
24. 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.
25. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen tau Yih, Tim Rocktäschel, Sebastian Riedel, and Douwe Kiela. 2021. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Preprint, arXiv:2005.11401.
26. Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, and Furu Wei. 2022. Dit: Self-supervised pre-training for document image transformer. In Proceedings of the 30th ACM International Conference on OpenBMB Rhapsody Group. 2024. Memex: Ocr-free visual document embedding model as your personal libr… [find](https://scholar.google.com/scholar?q=Junlong+Li%2C+Yiheng+Xu%2C+Tengchao+Lv%2C+Lei+Cui%2C+Cha+Zhang%2C+and+Furu+Wei%2E+2022%2E+Dit%3A+Self%2Dsupervised+pre%2Dtraining+for+document+image+transformer%2E+In+Proceedings+of+the+30th+ACM+International+Conference+on)
27. Ryota Tanaka, Taichi Iki, Taku Hasegawa, Kyosuke Nishida, Kuniko Saito, and Jun Suzuki. 2025. Vdocrag: Retrieval-augmented generation over visually-rich documents. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). [find](https://scholar.google.com/scholar?q=Ryota+Tanaka%2C+Taichi+Iki%2C+Taku+Hasegawa%2C+Kyosuke+Nishida%2C+Kuniko+Saito%2C+and+Jun+Suzuki%2E+2025%2E+Vdocrag%3A+Retrieval%2Daugmented+generation+over+visually%2Drich+documents%2E+In+Proceedings+of+the+IEEE%2FCVF+Confe)
28. Michał Turski, Tomasz Stanisławek, Karol Kaczmarek, Paweł Dyda, and Filip Graliński. 2023. Ccpdf: Building a high quality corpus for visually rich documents from web crawl data. In International Conference on Document Analysis and Recognition, pages 348–365. Springer. [find](https://scholar.google.com/scholar?q=Micha%C5%82+Turski%2C+Tomasz+Stanis%C5%82awek%2C+Karol+Kaczmarek%2C+Pawe%C5%82+Dyda%2C+and+Filip+Gralin%CC%81ski%2E+2023%2E+Ccpdf%3A+Building+a+high+quality+corpus+for+visually+rich+documents+from+web+crawl+data%2E+In+International+Conf)
29. Bin Wang, Chao Xu, Xiaomeng Zhao, Linke Ouyang, Fan Wu, Zhiyuan Zhao, Rui Xu, Kaiwen Liu, Yuan Qu, Fukai Shang, et al. 2024. Mineru: An open-source solution for precise document content extraction. arXiv preprint arXiv:2409.18839. [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+et+al%2E+2024%2E+Mineru%3A+An+open%2Dsource+solution+for+precise+document+content+extraction%2E+ar)
30. Haoran Wei, Chenglong Liu, Jinyue Chen, Jia Wang, Lingyu Kong, Yanming Xu, Zheng Ge, Liang Zhao, Jianjian Sun, Yuang Peng, Chunrui Han, and Xiangyu Zhang. 2024. General ocr theory: Towards ocr-2.0 via a unified end-to-end model. 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+Chunrui+Han%2C+and+Xiangyu+Zhang%2E+2024%2E+General+ocr+theory%3A+Towards+ocr%2D2%2E0+via)
31. Shi Yu, Chaoyue Tang, Bokai Xu, Junbo Cui, Junhao Ran, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, and Maosong Sun. 2025. Visrag: Vision-based retrieval-augmented generation on multi-modality documents. Preprint, arXiv:2410.10594. — [arXiv:2410.10594](https://arxiv.org/abs/2410.10594) [find](https://scholar.google.com/scholar?q=Shi+Yu%2C+Chaoyue+Tang%2C+Bokai+Xu%2C+Junbo+Cui%2C+Junhao+Ran%2C+Yukun+Yan%2C+Zhenghao+Liu%2C+Shuo+Wang%2C+Xu+Han%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2025%2E+Visrag%3A+Vision%2Dbased+retrieval%2Daugmented+generation+on+multi%2Dmoda)
32. Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, and Wentao Zhang. 2025. Ocr hinders rag: Evaluating the cascading impact of ocr on retrieval-augmented generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pag… [find](https://scholar.google.com/scholar?q=Junyuan+Zhang%2C+Qintong+Zhang%2C+Bin+Wang%2C+Linke+Ouyang%2C+Zichen+Wen%2C+Ying+Li%2C+Ka%2DHo+Chow%2C+Conghui+He%2C+and+Wentao+Zhang%2E+2025%2E+Ocr+hinders+rag%3A+Evaluating+the+cascading+impact+of+ocr+on+retrieval%2Daugmente)
33. Yian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei, Guanzhong Wang, Qingqing Dang, Yi Liu, and Jie Chen. 2024a. Detrs beat yolos on real-time object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16965–16974. [find](https://scholar.google.com/scholar?q=Yian+Zhao%2C+Wenyu+Lv%2C+Shangliang+Xu%2C+Jinman+Wei%2C+Guanzhong+Wang%2C+Qingqing+Dang%2C+Yi+Liu%2C+and+Jie+Chen%2E+2024a%2E+Detrs+beat+yolos+on+real%2Dtime+object+detection%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on)
34. Zhiyuan Zhao, Hengrui Kang, Bin Wang, and Conghui He. 2024b. Doclayout-yolo: Enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. 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+2024b%2E+Doclayout%2Dyolo%3A+Enhancing+document+layout+analysis+through+diverse+synthetic+data+and+global%2Dto%2Dlocal+adaptive+perception%2E+Preprint%2C+arXiv%3A)
35. Xu Zhong, Jianbin Tang, and Antonio Jimeno Yepes. 2019. Publaynet: largest dataset ever for document layout analysis. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 1015–1022. IEEE. [find](https://scholar.google.com/scholar?q=Xu+Zhong%2C+Jianbin+Tang%2C+and+Antonio+Jimeno+Yepes%2E+2019%2E+Publaynet%3A+largest+dataset+ever+for+document+layout+analysis%2E+In+2019+International+Conference+on+Document+Analysis+and+Recognition+%28ICDAR%29%2C+pag)

*Updated 31 October 2026*