Sofian Chaybouti

SofianChay's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model about 10 hours ago

tiiuae/Falcon-Perception-300M

Object Detection • Updated 2 days ago • 50 • 6

authored 3 papers 3 days ago

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity

Paper • 2404.03214 • Published Apr 4, 2024 • 3

VisRes Bench: On Evaluating the Visual Reasoning Capabilities of VLMs

Paper • 2512.21194 • Published Dec 24, 2025

Falcon Perception

Paper • 2603.27365 • Published 8 days ago • 12

liked a dataset 3 days ago

tiiuae/PBench

Viewer • Updated 5 days ago • 6.34k • 682 • 7

upvoted a paper 3 days ago

Falcon Perception

Paper • 2603.27365 • Published 8 days ago • 12

upvoted an article 4 days ago

view article

Article

Falcon Perception

• 

5 days ago

•

27

liked 2 models 5 days ago

tiiuae/Falcon-Perception

Mask Generation • Updated 2 days ago • 2.45k • 50

tiiuae/Falcon-OCR

Image-to-Text • Updated 4 days ago • 1.2k • 40

upvoted a collection 6 days ago

Falcon Perception

Collection

Falcon-Perception and Falcon-OCR model: early-fusion, natively multimodal, dense Autoregressive Transformer models. • 5 items • Updated 2 days ago • 12

upvoted a collection 18 days ago

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Collection

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). Stems from the CVPR 2026 AMoE paper. • 5 items • Updated 5 days ago • 10

updated 3 models 18 days ago

tiiuae/siglino-70M

Feature Extraction • 69.5M • Updated 18 days ago • 109 • 4

tiiuae/siglino-0.6B

Feature Extraction • 0.5B • Updated 18 days ago • 77 • 7

tiiuae/siglino-moe-0.15-0.6B

Feature Extraction • 0.5B • Updated 18 days ago • 73 • 3

liked a model 18 days ago

tiiuae/siglino-30M

Feature Extraction • 47.1M • Updated 18 days ago • 81 • 3

updated a model 18 days ago

tiiuae/siglino-30M

Feature Extraction • 47.1M • Updated 18 days ago • 81 • 3

updated a collection 19 days ago

SigLino: Vision Foundation Models (SigLIP2 + DINOv3)

Collection

Vision encoders distilled from DINOv3 and SigLIP2 (MoE & Dense). Stems from the CVPR 2026 AMoE paper. • 5 items • Updated 5 days ago • 10

published a model 19 days ago

tiiuae/siglino-30M

Feature Extraction • 47.1M • Updated 18 days ago • 81 • 3