PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
• 32
AI & ML interests
Deep Learning Framework
Recent Activity
View all activity
Papers
GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Articles
Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 10.8k • 1.61k -
PaddleOCR-VL Online Demo
📈245Extract text, tables, formulas, and charts from images
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 128 -
PaddlePaddle/PP-DocLayoutV2
Object Detection • Updated • 8.46k • 30
PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese
-
PaddlePaddle/arabic_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 2.56k • 3 -
PaddlePaddle/chinese_cht_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 71 • 1 -
PaddlePaddle/cyrillic_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 1.74k • 1 -
PaddlePaddle/devanagari_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 1.59k • 1
Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
-
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 10.8k • 1.61k -
PaddleOCR-VL Online Demo
📈245Extract text, tables, formulas, and charts from images
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 128 -
PaddlePaddle/PP-DocLayoutV2
Object Detection • Updated • 8.46k • 30
PP-StructureV3 is a SOTA document parsing solution on OmniDocBench, supporting the conversion of PDFs and do cument images to Markdown and JSON.
PP-OCRv5 is the latest text recognition solution, supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese
-
PaddlePaddle/arabic_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 2.56k • 3 -
PaddlePaddle/chinese_cht_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 71 • 1 -
PaddlePaddle/cyrillic_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 1.74k • 1 -
PaddlePaddle/devanagari_PP-OCRv3_mobile_rec
Image-to-Text • Updated • 1.59k • 1