11 39 74

youssef boulaouane

byoussef

Boulaouaney

AI & ML interests

None yet

Recent Activity

liked a Space 1 day ago

alexnasa/Chain-of-Zoom

upvoted a collection 12 days ago

Gemma 3n Preview

liked a model 12 days ago

google/gemma-3n-E4B-it-litert-preview

View all activity

Organizations

byoussef's activity

liked a Space 1 day ago

Chain-of-Zoom

🚀

Extreme Super-Resolution via Scale Autoregression

upvoted a collection 12 days ago

Gemma 3n Preview

Collection

2 items • Updated 3 days ago • 96

liked a model 12 days ago

google/gemma-3n-E4B-it-litert-preview

Image-Text-to-Text • Updated 7 days ago • 801

liked a model 14 days ago

facebook/KernelLLM

Text Generation • Updated 7 days ago • 11.2k • 140

liked a Space 24 days ago

Qwen Od

📈

Detect objects in images from URL or upload

upvoted a paper about 2 months ago

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 164

liked a Space 2 months ago

7.58k

DeepSite

🐳

Generate any application with DeepSeek

reacted to jasoncorkill's post with 🔥 2 months ago

Post

2264

🔥 It's out! We published the dataset for our evaluation of @OpenAI 's new 4o image generation model.

Rapidata/OpenAI-4o_t2i_human_preference

Yesterday we published the first large evaluation of the new model, showing that it absolutely leaves the competition in the dust. We have now made the results and data available here! Please check it out and ❤️ !

liked 2 Spaces 2 months ago

1.21k

InstantCoder

🦀

Generate app code with your idea

966

InfiniteYou-FLUX

📸

Flexible Photo Recrafting While Preserving Your Identity

upvoted an article 3 months ago

Article

Open-Source Handwritten Signature Detection Model

•

Mar 14

• 113

liked 2 Spaces 3 months ago

175

Remade Effects

🦀

Generate a video from an image with a chosen effect

281

Thera Arbitrary-Scale Super-Resolution

🔥

Enhance image quality with real-time super-resolution

upvoted a collection 3 months ago

SigLIP2

Collection

36 items • Updated 3 days ago • 74

liked a Space 3 months ago

2.64k

The Ultra-Scale Playbook

🌌

The ultimate guide to training LLM on large GPU Clusters

reacted to tianchez's post with 🚀 4 months ago

Post

4419

Introducing VLM-R1!

GRPO has helped DeepSeek R1 to learn reasoning. Can it also help VLMs perform stronger for general computer vision tasks?

The answer is YES and it generalizes better than SFT. We trained Qwen 2.5 VL 3B on RefCOCO (a visual grounding task) and eval on RefCOCO Val and RefGTA (an OOD task).

https://github.com/om-ai-lab/VLM-R1