-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 111 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.99M • 3.11k -
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 14.3k • 1.5k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 84k • 482
www.minds.com/jelyazko/
21world
AI & ML interests
Who not work will not Eat
Recent Activity
updated
a collection
43 minutes ago
18\ other models
updated
a collection
about 1 hour ago
18\ other models
updated
a collection
about 7 hours ago
18\ other models
Organizations
-
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 111 -
deepseek-ai/DeepSeek-OCR
Image-Text-to-Text • 3B • Updated • 2.99M • 3.11k -
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text • 1.0B • Updated • 14.3k • 1.5k -
nanonets/Nanonets-OCR2-3B
Image-Text-to-Text • 4B • Updated • 84k • 482
67 \ vision -> 3d printer/lathe/.../.../ control
datasets
0
None public yet