PaddleOCR-VL - a PaddlePaddle Collection

PaddlePaddle 's Collections

PaddleOCR-VL

updated 10 days ago

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

PaddlePaddle/PaddleOCR-VL

Image-Text-to-Text • 1.0B • Updated 4 days ago • 17.3k • 1.11k
Running

145

145

PaddleOCR-VL Online Demo

📈

Recognize text and elements in images
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published 12 days ago • 71