PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper
•
2510.14528
•
Published
•
111
Blessing Agyei Kyem
Blessing988
AI & ML interests
Intelligent Transportation Systems
Connected and Autonomous Vehicles
Multi-Agent Reinforcement Learning
Recent Activity
liked
a model
about 2 months ago
llava-hf/llama3-llava-next-8b-hf
liked
a dataset
about 2 months ago
lmms-lab/ai2d
Organizations
None yet
upvoted
a
paper
2 months ago
upvoted
3
collections
5 months ago
upvoted
3
articles
6 months ago
Article
nanoVLM: The simplest repository to train your VLM in pure PyTorch
- +5
•
247
Article
A Dive into Vision-Language Models
•
81
Article
Vision Language Models Explained
•
505
upvoted
a
collection
6 months ago
upvoted
2
papers
6 months ago
upvoted
a
collection
8 months ago
upvoted
3
articles
8 months ago
Article
Vision Language Models (Better, faster, stronger)
- +3
•
580
Article
Preference Optimization for Vision Language Models
- +2
•
89
Article
SmolVLM2: Bringing Video Understanding to Every Device
- +5
•
320
upvoted
a
collection
8 months ago
upvoted
an
article
8 months ago
Article
Fine-tune Llama 3 with ORPO
•
241
upvoted
2
papers
over 1 year ago
upvoted
2
articles
over 1 year ago
Article
Llama 3.1 - 405B, 70B & 8B with multilinguality and long context
- +6
•
241
Article
SmolLM - blazingly fast and remarkably powerful
- +1
•
436