PP-OCRv6 Collection From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks • 19 items • Updated 20 days ago • 101
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model Paper • 2510.14528 • Published Oct 16, 2025 • 129
view article Article Unleashing the Full Potential of ERNIE4.5 using FastDeploy baidu • Sep 19, 2025 • 11
view article Article PP-OCRv5 on Hugging Face: A Specialized Approach to OCR baidu • Sep 10, 2025 • 112