In a Training Loop 🔄

14 52 96

youssef boulaouane

byoussef

Boulaouaney

AI & ML interests

None yet

Recent Activity

liked a model 12 days ago

tencent/HunyuanOCR

liked a model 12 days ago

Tongyi-MAI/Z-Image-Turbo

liked a model 24 days ago

depth-anything/DA3NESTED-GIANT-LARGE

View all activity

Organizations

liked 2 models 12 days ago

tencent/HunyuanOCR

Image-Text-to-Text • 1.0B • Updated 9 days ago • 521k • 658

Tongyi-MAI/Z-Image-Turbo

Text-to-Image • Updated 3 days ago • 233k • • 2.5k

liked 2 models 24 days ago

depth-anything/DA3NESTED-GIANT-LARGE

Depth Estimation • 2B • Updated 28 days ago • 128k • 39

depth-anything/DA3METRIC-LARGE

Depth Estimation • Updated 27 days ago • 31.9k • 7

liked a Space 24 days ago

Depth Anything 3

🏢

309

Generate depth maps from images using GPU acceleration

upvoted a collection 24 days ago

Depth Anything 3

Collection

9 items • Updated 7 days ago • 22

upvoted a paper 29 days ago

Persistent Anti-Muslim Bias in Large Language Models

Paper • 2101.05783 • Published Jan 14, 2021 • 2

upvoted 2 articles 29 days ago

Article

Converting Models to Core ML

Sep 4, 2024

•

Article

Unleash ML Power on iOS: Apple Silicon Optimization Secrets

Jul 18, 2024

•

upvoted a collection 29 days ago

MetaCLIP2 Multilingual

Collection

8 items • Updated 29 days ago • 15

upvoted a paper 29 days ago

MetaCLIP 2: A Worldwide Scaling Recipe

Paper • 2507.22062 • Published Jul 29 • 36

liked a model about 2 months ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4 • 5.39M • 2.95k

reacted to merve's post with 🚀 about 2 months ago

Post

6689

deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages

4 replies

upvoted a paper about 2 months ago

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

Paper • 2411.19331 • Published Nov 28, 2024 • 5

liked a model 3 months ago

Qwen/Qwen-Image-Edit-2509

Image-to-Image • Updated Sep 22 • 600k • • 940

reacted to vikhyatk's post with 🔥 3 months ago

Post

4622

Just released a preview of Moondream 3! moondream/moondream3-preview

This is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.

More details in the release blog post: https://moondream.ai/blog/moondream-3-preview