mlsanityData to 7 Oct 2026

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

arXiv 2510.14528 ↗First posted 16 Oct 2025cs.CVcited by 84

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

In this report, we propose PaddleOCR-VL, a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. Code is available at https://github.com/PaddlePaddle/PaddleOCR .

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 31 of its 77 references that are in the map. First posted on arXiv 16 Oct 2025.

Builds on

31 of 77 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing26 Sep
  2. 2025POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversion1 Sep
  3. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model18 Aug
  4. 2025SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion14 Mar
  5. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models25 Feb
  6. 2025Ocean-OCR: Towards General OCR Application via a Vision-Language Model26 Jan

Other references · 25

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  7. 2022ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoningcited by 1,449
  8. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  9. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,061
  10. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 397
  11. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 255
  12. 2023Nougat: Neural Optical Understanding for Academic Documentscited by 240
13 more
  1. 2024General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Modelcited by 174
  2. 2022Chart-to-Text: A Large-Scale Benchmark for Chart Summarizationcited by 166
  3. 2023UniChart: A Universal Vision-language Pretrained Model for Chart Comprehension and Reasoningcited by 158
  4. 2022DePlot: One-shot visual language reasoning by plot-to-table translationcited by 157
  5. 2025PaddleOCR 3.0 Technical Reportcited by 136
  6. 2023VisText: A Benchmark for Semantically Rich Chart Captioningcited by 111
  7. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  8. 2021LayoutReader: Pre-training of Text and Layout for Reading Order Detectioncited by 79
  9. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 78
  10. 2024TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learningcited by 51
  11. 2025Kwai Keye-VL Technical Reportcited by 47
  12. 2024UniMERNet: A Universal Network for Real-World Mathematical Expression Recognitioncited by 41
  13. 2025PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Constructioncited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 74.

84 papers.

Sort:

By area:

  1. 2026DeepSeek-OCR 2: Visual Causal Flowcited by 68
  2. 2026PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsingcited by 54
  3. 2025olmOCR 2: Unit Test Rewards for Document OCRcited by 41
  4. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 26
  5. 2026GLM-OCR Technical Reportcited by 24
  6. 2026LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCRcited by 22
  7. 2026MobileDreamer: Generative Sketch World Model for GUI Agentcited by 21
  8. 2026Dolphin-v2: Universal Document Parsing via Scalable Anchor Promptingcited by 20
  9. 2026PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Trainingcited by 20
  10. 2025HunyuanOCR Technical Reportcited by 18
  11. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  12. 2025UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameterscited by 12
38 more
  1. 2026FireRed-OCR Technical Reportcited by 12
  2. 2026Multimodal OCR: Parse Anything from Documentscited by 12
  3. 2026Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wildcited by 11
  4. 2026OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Modelscited by 10
  5. 2026Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decodingcited by 9
  6. 2025DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translationcited by 8
  7. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 8
  8. 2026Unlimited OCR Workscited by 8
  9. 2026GDRO: Group-level Reward Post-training Suitable for Diffusion Modelscited by 7
  10. 2025Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCRcited by 7
  11. 2026Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Trainingcited by 7
  12. 2026DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Searchcited by 6
  13. 2025SO-Bench: A Structural Output Evaluation of Multimodal LLMscited by 5
  14. 2026HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decodingcited by 5
  15. 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generationcited by 5
  16. 2026Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characterscited by 5
  17. 2026OvisOCR2 Technical Reportcited by 5
  18. 2025TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognitioncited by 4
  19. 2025Benchmarking Document Parsers on Mathematical Formula Extraction from PDFscited by 4
  20. 2026Logics-Parsing-Omni Technical Reportcited by 4
  21. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 4
  22. 2026CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoningcited by 4
  23. 2026Infinity-Parser2 Technical Reportcited by 4
  24. 2025Uni-Parser Technical Reportcited by 3
  25. 2026CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agentscited by 3
  26. 2026ABot-OCR Technical Reportcited by 3
  27. 2026VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generationcited by 2
  28. 2026Efficient Document Parsing via Parallel Token Predictioncited by 2
  29. 2026ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formatscited by 2
  30. 2026RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wildcited by 2
  31. 2026StrucTab: A Structured Optimization Framework for Table Parsingcited by 2
  32. 2026MORE: A Multilingual Document Parsing Benchmark and Evaluationcited by 2
  33. 2025SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Designcited by 1
  34. 2026Benchmarking Vision-Language Models for French PDF-to-Markdown Conversioncited by 1
  35. 2026LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Referencecited by 1
  36. 2026SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asiacited by 1
  37. 2026TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignmentcited by 1
  38. 2026A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documentscited by 1

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing
  2. 2026MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
  3. 2026Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
  4. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns
  5. 2025DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
  6. 2024TAP-VL: Text Layout-Aware Pre-training for Enriched Vision-Language Models
  7. 2026DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
  8. 2024Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction