Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: 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 .
Authors (18)
Cheng Cui
Ting Sun
Suyin Liang
Tingquan Gao
Zelun Zhang
Jiaxuan Liu
+12 more
Submitted
October 16, 2025
Key Contributions
PaddleOCR-VL introduces PaddleOCR-VL-0.9B, an ultra-compact VLM that integrates a dynamic resolution visual encoder with ERNIE-4.5-0.3B for accurate multilingual document parsing. It achieves SOTA performance across 109 languages for complex element recognition while maintaining minimal resource consumption and fast inference.
Business Value
Enables efficient and accurate processing of diverse multilingual documents, automating tasks like data entry, information retrieval, and knowledge management for global businesses.