mlsanityData to 14 Oct 2026

PaddleOCR 3.0 Technical Report

arXiv 2507.05595 ↗First posted 8 Jul 2025cs.CVcited by 143

Not on the map. Why?

Cited by 34 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In addition to offering a high-quality OCR model library, PaddleOCR 3.0 provides efficient tools for training, inference, and deployment, supports heterogeneous hardware acceleration, and enables developers to easily build intelligent document applications.

Key facts. Cited by 143 papers in the map (data through 14 Oct 2026). Builds on 24 of its 42 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

24 of 42 references.

References · 24

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  7. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 520
  8. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  9. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 180
  10. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 151
  11. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 150
  12. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 125
12 more
  1. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 106
  2. 2022SVTR: Scene Text Recognition with a Single Visual Modelcited by 88
  3. 2013Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networkscited by 84
  4. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversioncited by 53
  5. 2020GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognitioncited by 52
  6. 2021PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR Systemcited by 39
  7. 2021PP-LCNet: A Lightweight CPU Convolutional Neural Networkcited by 27
  8. 2025PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Constructioncited by 26
  9. 2022PP-StructureV2: A Stronger Document Analysis Systemcited by 20
  10. 2023UVDoc: Neural Grid-based Document Unwarpingcited by 16
  11. 2025PP-FormulaNet: Bridging Accuracy and Efficiency in Advanced Formula Recognitioncited by 7
  12. 2025PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Trickscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 41; 2026: 102.

143 papers.

Sort:

By area:

  1. 2025LongCat-Image Technical Reportcited by 100
  2. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 89
  3. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 77
  4. 2025Detect Anything via Next Point Predictioncited by 73
  5. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 57
  6. 2025Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matchingcited by 56
  7. 2026Infinite Worlds with Versatile Interactionscited by 48
  8. 2025dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Modelcited by 47
  9. 2026SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecturecited by 32
  10. 2026InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editingcited by 28
  11. 2026LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decodingcited by 28
  12. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 27
38 more
  1. 2025Region-Constraint In-Context Generation for Instructional Video Editingcited by 23
  2. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  3. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 22
  4. 2026Qianfan-OCR: A Unified End-to-End Model for Document Intelligencecited by 21
  5. 2026PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Trainingcited by 21
  6. 2025HunyuanOCR Technical Reportcited by 20
  7. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  8. 2026DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editingcited by 14
  9. 2026Multimodal OCR: Parse Anything from Documentscited by 14
  10. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  11. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patternscited by 13
  12. 2025UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameterscited by 13
  13. 2025ThinkGen: Generalized Thinking for Visual Generationcited by 13
  14. 2026FireRed-OCR Technical Reportcited by 13
  15. 2026LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Modelcited by 13
  16. 2025IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?cited by 12
  17. 2026OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Modelscited by 12
  18. 2026PromptRL: Prompt Matters in RL for Flow-Based Image Generationcited by 12
  19. 2026DM0: An Embodied-Native Vision-Language-Action Model towards Physical AIcited by 12
  20. 2026Lance: Unified Multimodal Modeling by Multi-Task Synergycited by 12
  21. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Modelcited by 10
  22. 2026SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metricscited by 10
  23. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 10
  24. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 10
  25. 2025Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCRcited by 9
  26. 2026Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPOcited by 9
  27. 2026PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedbackcited by 9
  28. 2025Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculationcited by 8
  29. 2026MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decodingcited by 8
  30. 2025Qianfan-VL: Domain-Enhanced Universal Vision-Language Modelscited by 7
  31. 2025Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understandingcited by 7
  32. 2025RubricRL: Simple Generalizable Rewards for Text-to-Image Generationcited by 7
  33. 2026Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Trainingcited by 7
  34. 2026V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Thinkcited by 7
  35. 2025AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Fieldcited by 6
  36. 2025DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLMcited by 6
  37. 2026HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decodingcited by 6
  38. 2026Beyond NL2Code: A Structured Survey of Multimodal Code Intelligencecited by 6

50 most cited of 143 All 143 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Ocean-OCR: Towards General OCR Application via a Vision-Language Model
  2. 2026DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
  3. 2026PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks
  4. 2024TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
  5. 2026Typhoon OCR: Open Vision-Language Model For Thai Document Extraction
  6. 2025Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
  7. 2026PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks
  8. 2026OCRTurk: A Comprehensive OCR Benchmark for Turkish