mlsanityData to 7 Oct 2026

PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing

arXiv 2601.21957 ↗First posted 29 Jan 2026cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions, including scanning, skew, warping, screen-photography, and illumination, we propose the Real5-OmniDocBench benchmark. Experimental results demonstrate that this enhanced model attains SOTA performance on the newly curated benchmark. Furthermore, we extend the model's capabilities by incorporating seal recognition and text spotting tasks, while remaining a 0.9B ultra-compact VLM with high efficiency. Code: https://github.com/PaddlePaddle/PaddleOCR

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

25 of 33 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  7. 2025Qwen2.5-VL Technical Reportcited by 5,418
  8. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  9. 2025InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiencycited by 1,419
  10. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  12. 2023Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolutioncited by 226
13 more
  1. 2025DeepSeek-OCR: Contexts Optical Compressioncited by 174
  2. 2024OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotationscited by 144
  3. 2025PaddleOCR 3.0 Technical Reportcited by 136
  4. 2025olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Modelscited by 120
  5. 2025MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsingcited by 108
  6. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 84
  7. 2025MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigmcited by 81
  8. 2025Dolphin: Document Image Parsing via Heterogeneous Anchor Promptingcited by 78
  9. 2025Detect Anything via Next Point Predictioncited by 66
  10. 2024Image Over Text: Transforming Formula Recognition Evaluation with Character Detection Matchingcited by 39
  11. 2025POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversioncited by 34
  12. 2025PP-DocLayout: A Unified Document Layout Detection Model to Accelerate Large-Scale Data Constructioncited by 26
  13. 2025MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patternscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 54.

54 papers.

Sort:

By area:

  1. 2026MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scalecited by 26
  2. 2026GLM-OCR Technical Reportcited by 24
  3. 2026Qianfan-OCR: A Unified End-to-End Model for Document Intelligencecited by 20
  4. 2026PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Trainingcited by 20
  5. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Bettercited by 14
  6. 2026FireRed-OCR Technical Reportcited by 12
  7. 2026Multimodal OCR: Parse Anything from Documentscited by 12
  8. 2026Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wildcited by 11
  9. 2026JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generationcited by 10
  10. 2026VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?cited by 8
  11. 2026MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generationcited by 8
  12. 2026AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generationcited by 5
38 more
  1. 2026OvisOCR2 Technical Reportcited by 5
  2. 2026Logics-Parsing-Omni Technical Reportcited by 4
  3. 2026MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarioscited by 4
  4. 2026MonkeyOCRv2: A Visual-Text Foundation Model for Document AIcited by 4
  5. 2026ABot-OCR Technical Reportcited by 3
  6. 2026GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scriptscited by 2
  7. 2026LensVLM: Selective Context Expansion for Compressed Visual Representation of Textcited by 2
  8. 2026DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understandingcited by 2
  9. 2026ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formatscited by 2
  10. 2026What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Mediacited by 2
  11. 2026ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correctioncited by 2
  12. 2026RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wildcited by 2
  13. 2026Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Modelscited by 2
  14. 2026LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Referencecited by 1
  15. 2026Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Modelscited by 1
  16. 2026MinerU-Popo: Universal Post-Processing Model for Structured Document Parsingcited by 1
  17. 2026Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Carecited by 1
  18. 2026PaDoc: Layout-Grounded Parallel Decoding for Document Parsingcited by 1
  19. 2026FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarkscited by 1
  20. 2026OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvementcited by 1
  21. 2026Texo: Formula Recognition within 20M Parameterscited by 0
  22. 2026MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsingcited by 0
  23. 2026Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsingcited by 0
  24. 2026Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoningcited by 0
  25. 2026Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Whycited by 0
  26. 2026An LMM for Precisely Grounding Elements in Documentscited by 0
  27. 2026How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbationscited by 0
  28. 2026ClinOCR-Bench: A Comprehensive Clinical Scanned Document Dataset for Optical Character Recognition Model Evaluationcited by 0
  29. 2026HPD-Parsing: Hierarchical Parallel Document Parsingcited by 0
  30. 2026Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-Oncited by 0
  31. 2026When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documentscited by 0
  32. 2026DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoningcited by 0
  33. 2026TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documentscited by 0
  34. 2026TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documentscited by 0
  35. 2026LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documentscited by 0
  36. 2026Benchmarking Clinical Decision Pathway Adherence in Large Language Modelscited by 0
  37. 2026Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoningcited by 0
  38. 2026WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsingcited by 0

50 most cited of 54 All 54 (JSON)