PaddleOCR-VL - a PaddlePaddle Collection

PaddlePaddle 's Collections

PaddleOCR-VL

updated 11 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 5 days ago • 18.7k • 1.14k
Running

150

150

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 13 days ago • 72