Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
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
Organization Card
PaddlePaddle on the Huggingface Hub
spaces
7
pinned
Running
Featured
228
PaddleOCR-VL Online Demo
📈
Parse and recognize text in images
Running
9
PaddleOCR-VL-1.5 Online Demo
😻
PaddleOCR-VL-1.5_Online_Demo
Running
8
Doc2Page - Document to Webpage Converter
🏄
Convert docs to webpages using PaddleOCR and ERNIE
Running
77
PP-OCRv5 Online Demo
🌍
Universal-Scene Text Recognition Model with High-Accuracy
Running
32
PP-StructureV3 Online Demo
📊
Next-Gen High-Precision Doc Parsing Solution
models
82
PaddlePaddle/PP-DocLayoutV3
Image Segmentation
•
Updated
•
5
PaddlePaddle/PP-DocLayoutV3_safetensors
Object Detection
•
Updated
•
2
PaddlePaddle/PaddleOCR-VL-1.5
Image-Text-to-Text
•
1.0B
•
Updated
•
82
PaddlePaddle/PP-DocLayoutV2
Object Detection
•
Updated
•
17.3k
•
21
PaddlePaddle/PP-OCRv5_server_det_safetensors
Updated
•
19
•
1
PaddlePaddle/PP-OCRv5_mobile_det_safetensors
Updated
•
14
•
1
PaddlePaddle/PP-DocLayoutV2_safetensors
Updated
•
21
•
2
PaddlePaddle/PaddleOCR-VL
Image-Text-to-Text
•
1.0B
•
Updated
•
16k
•
1.52k
PaddlePaddle/devanagari_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
570
PaddlePaddle/latin_PP-OCRv5_mobile_rec
Image-to-Text
•
Updated
•
30.1k
•
1