mlsanityData to 7 Oct 2026

PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

arXiv 2606.13108 ↗First posted 11 Jun 2026cs.CVcited by 12

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

Abstract (arXiv)

Vision-Language Models (VLMs) have achieved impressive results on general vision-language tasks, yet they suffer from hallucination, imprecise localization, and prohibitive computational cost when applied to dedicated OCR scenarios. This paper presents PP-OCRv6, a lightweight OCR system that combines architectural innovation with data-centric optimization. PP-OCRv6 redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization, decoupling spatial token mixing from channel mixing and supporting both tasks through task-specific stride configurations. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. On our in-house benchmarks, PP-OCRv6medium achieves 83.2% recognition accuracy and 86.2% detection Hmean, outperforming PP-OCRv5server by +5.1% and +4.6% respectively while surpassing Qwen3-VL-235B, GPT-5.5, and Gemini-3.1-Pro with orders of magnitude fewer parameters. The tiny tier achieves 3.9× faster inference than PP-OCRv5mobile on Intel Xeon CPU while maintaining comparable accuracy.

Key facts. Cited by 12 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 17 of its 20 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

17 of 20 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026PP-OCRv5: A Specialized 5M-Parameter Model Rivaling Billion-Parameter Vision-Language Models on OCR Tasks25 Mar

Other references · 16

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2025Qwen3 Technical Reportcited by 8,195
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  6. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  8. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  9. 2014Deeply-Supervised Netscited by 364
  10. 2020PP-OCR: A Practical Ultra Lightweight OCR Systemcited by 147
  11. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  12. 2022PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR Systemcited by 105
4 more
  1. 2018NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognitioncited by 73
  2. 2020GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognitioncited by 52
  3. 2021PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR Systemcited by 39
  4. 2021PP-LCNet: A Lightweight CPU Convolutional Neural Networkcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026Depth-Only Open-Vocabulary 3D Semantic Segmentation For Privacy-Preserving Robotic Applicationscited by 1
  2. 2026Exploring the Performance Frontier of Compact Unified Image Generation Modelscited by 1
  3. 2026All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Expertscited by 1
  4. 2026SCOPE-Router: Cost-Aware Open-Set VLM Routing for Execution-Oriented Taskscited by 0
  5. 2026Charts Are Beyond Pixels: Probing for Layer-Wise Chart Understanding and Editingcited by 0
  6. 2026A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognitioncited by 0
  7. 2026Privacy-Preserving Semantic Segmentation from High-Resolution Depth and Ultra-Low-Resolution RGBcited by 0
  8. 2026Enhanced Video Text Editing with Trajectory-Aligned Glyph Renderingcited by 0
  9. 2026PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligencecited by 0
  10. 2026HelixWorld: A Real-time Interactive Audio-Visual World Modelcited by 0
  11. 2026NextMe-800: Anticipating Personal Behavior from Months of Egocentric Videocited by 0
  12. 2026HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image Restorationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking Vision-Language Models on Optical Character Recognition in Dynamic Video Environments
  2. 2026HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
  3. 2026Where Vision Becomes Text: Locating the OCR Routing Bottleneck in Vision-Language Models
  4. 2025Ocean-OCR: Towards General OCR Application via a Vision-Language Model
  5. 2026LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
  6. 2026From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists
  7. 2024TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens
  8. 2025DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model