mlsanityData to 14 Oct 2026

MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm

arXiv 2506.05218 ↗First posted 5 Jun 2025cs.CVcited by 87

Not on the map. Why?

Cited by 26 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce MonkeyOCR, a document parsing model that advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm. This design simplifies what would otherwise be a complex multi-tool pipeline and avoids the inefficiencies of processing full pages with giant end-to-end models. In SRR, document parsing is abstracted into three fundamental questions - ``Where is it?'' (structure), ``What is it?'' (recognition), and ``How is it organized?'' (relation) - corresponding to structure detection, content recognition, and relation prediction. To support this paradigm, we present MonkeyDoc, a comprehensive dataset with 4.5 million bilingual instances spanning over ten document types, which addresses the limitations of existing datasets that often focus on a single task, language, or document type. Leveraging the SRR paradigm and MonkeyDoc, we trained a 3B-parameter document foundation model. We further identify parameter redundancy in this model and propose contiguous parameter degradation (CPD), enabling the construction of models from 0.6B to 1.2B parameters that run faster with acceptable performance drop. MonkeyOCR achieves state-of-the-art performance, surpassing previous open-source and closed-source methods, including Gemini 2.5-Pro. Additionally, the model can be efficiently deployed for inference on a single RTX 3090 GPU. Code and models will be released at https://github.com/Yuliang-Liu/MonkeyOCR.

Key facts. Cited by 87 papers in the map (data through 14 Oct 2026). Builds on 43 of its 65 references that are in the map. First posted on arXiv 5 Jun 2025.

Builds on

43 of 65 references.

References · 43

  1. 2025Qwen2.5-VL Technical Reportcited by 5,587
  2. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  3. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  4. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  5. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  6. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  7. 2023OCRBench: On the Hidden Mystery of OCR in Large Multimodal Modelscited by 476
  8. 2021OCR-free Document Understanding Transformercited by 407
  9. 2024ShortGPT: Layers in Large Language Models are More Redundant Than You Expectcited by 383
  10. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 357
  11. 2019PubLayNet: largest dataset ever for document layout analysiscited by 351
  12. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 316
31 more
  1. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  2. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 245
  3. 2019Image-based table recognition: data, model, and evaluationcited by 237
  4. 2024The Unreasonable Ineffectiveness of the Deeper Layerscited by 226
  5. 2015Evaluation of Deep Convolutional Nets for Document Image Classification and Retrievalcited by 213
  6. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 180
  7. 2024TextMonkey: An OCR-Free Large Multimodal Model for Understanding Documentcited by 174
  8. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  9. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 148
  10. 2020Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Contextcited by 147
  11. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 125
  12. 2024mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understandingcited by 114
  13. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 106
  14. 2024DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perceptioncited by 82
  15. 2021LayoutReader: Pre-training of Text and Layout for Reading Order Detectioncited by 80
  16. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 79
  17. 2020Tabular Transformers for Modeling Multivariate Time Seriescited by 77
  18. 2024OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognitioncited by 74
  19. 2022Syntax-Aware Network for Handwritten Mathematical Expression Recognitioncited by 68
  20. 2022XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understandingcited by 68
  21. 2023SPTS v2: Single-Point Scene Text Spottingcited by 66
  22. 2025Docling: An Efficient Open-Source Toolkit for AI-driven Document Conversioncited by 63
  23. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 53
  24. 2023Vision Grid Transformer for Document Layout Analysiscited by 47
  25. 2023M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysiscited by 46
  26. 2021SPTS: Single-Point Text Spottingcited by 45
  27. 2024UniMERNet: A Universal Network for Real-World Mathematical Expression Recognitioncited by 42
  28. 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTMLcited by 39
  29. 2024DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Modelscited by 36
  30. 2021PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Table Image Recognition to Latexcited by 10
  31. 2025XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmarkcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 20; 2026: 67.

87 papers.

Sort:

By area:

  1. 2025DeepSeek-OCR: Contexts Optical Compressioncited by 183
  2. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 116
  3. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 89
  4. 2026DeepSeek-OCR 2: Visual Causal Flowcited by 74
  5. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 57
  6. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 47
  7. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 27
  8. 2026GLM-OCR Technical Reportcited by 26
  9. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 22
  10. 2026PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Trainingcited by 21
  11. 2025HunyuanOCR Technical Reportcited by 20
  12. 2026TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Renderingcited by 15
38 more
  1. 2026Multimodal OCR: Parse Anything from Documentscited by 14
  2. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  3. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patternscited by 13
  4. 2025UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameterscited by 13
  5. 2026FireRed-OCR Technical Reportcited by 13
  6. 2025MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrievalcited by 12
  7. 2026OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Modelscited by 12
  8. 2026Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wildcited by 12
  9. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Modelcited by 10
  10. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 10
  11. 2025DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translationcited by 9
  12. 2025Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCRcited by 9
  13. 2026MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decodingcited by 8
  14. 2026Unlimited OCR Workscited by 8
  15. 2026Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Trainingcited by 7
  16. 2025Advanced Layout Analysis Models for Doclingcited by 6
  17. 2025DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLMcited by 6
  18. 2026HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decodingcited by 6
  19. 2026DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understandingcited by 6
  20. 2026Beyond NL2Code: A Structured Survey of Multimodal Code Intelligencecited by 6
  21. 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generationcited by 5
  22. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 5
  23. 2026OvisOCR2 Technical Reportcited by 5
  24. 2025Baseer: A Vision-Language Model for Arabic Document-to-Markdown OCRcited by 4
  25. 2025TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognitioncited by 4
  26. 2025Benchmarking Document Parsers on Mathematical Formula Extraction from PDFscited by 4
  27. 2026How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settingscited by 4
  28. 2026MonkeyOCRv2: A Visual-Text Foundation Model for Document AIcited by 4
  29. 2025DocTron-Formula: Generalized Formula Recognition in Complex and Structured Scenarioscited by 3
  30. 2025Uni-Parser Technical Reportcited by 3
  31. 2026Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processingcited by 3
  32. 2026ABot-OCR Technical Reportcited by 3
  33. 2025MolSight: Optical Chemical Structure Recognition with SMILES Pretraining, Multi-Granularity Learning and Reinforcement Learningcited by 2
  34. 2026LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Referencecited by 2
  35. 2026Efficient Document Parsing via Parallel Token Predictioncited by 2
  36. 2026SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asiacited by 2
  37. 2026Beyond String Matching: Semantic Evaluation of PDF Table Extractioncited by 2
  38. 2026The Character Error Vector: Decomposable errors for page-level OCR evaluationcited by 2

50 most cited of 87 All 87 (JSON)