Youssef Boulaouane's picture

Youssef Boulaouane

joseph-bou

·

AI & ML interests

None yet

Recent Activity

liked a model 6 days ago

Qwen/Qwen-Image-2512

liked a Space 11 days ago

Reubencf/Nano_Banana_Editor

liked a dataset 20 days ago

google/mobile-actions

View all activity

Organizations

upvoted 3 collections about 2 months ago

SAM3

5 items • Updated Nov 19, 2025 • 119

SAM3

4 items • Updated Nov 19, 2025 • 23

Depth Anything 3

12 items • Updated about 1 month ago • 25

upvoted an article 2 months ago

Article

huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning

+2

Oct 27, 2025

•

74

upvoted a collection 3 months ago

MobileCLIP2

MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 37 items • Updated Sep 18, 2025 • 57

upvoted an article 3 months ago

Article

SOTA OCR with Core ML and dots.ocr

Oct 2, 2025

•

62

upvoted 4 collections 4 months ago

Qwen3-Omni

6 items • Updated 11 days ago • 179

Qwen3-VL

37 items • Updated 11 days ago • 562

MobileCLIP-2

OpenCLIP / timm ports of Apple's MobileCLIP-2 multi-modal and image encoders • 12 items • Updated Sep 19, 2025 • 1

timm DINOv3

Meta AI's DINOv3 weights in timm. ViTs with `qkvb` have a zero QV bias present, otherwise bias is disabled. QKV bias are all 0 in original weights. • 18 items • Updated Sep 19, 2025 • 26

upvoted an article 4 months ago

Article

AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models

Sep 16, 2025

•

19

upvoted 4 collections 4 months ago

iOS Models

LiteRT models that can run on iOS • 5 items • Updated about 1 month ago • 4

Android Models

LiteRT models that can run on Android • 20 items • Updated about 1 month ago • 163

YanoljaNEXT-Rosetta

Translation Model for JSON-Structured Data • 3 items • Updated Sep 3, 2025 • 9

FastVLM

Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2, 2025 • 106

upvoted 2 collections 5 months ago

Aug 22 Releases

35 items • Updated Aug 27, 2025 • 3

InternVL3.5

This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). • 54 items • Updated Sep 28, 2025 • 104

upvoted a collection 6 months ago

Perception Encoder

OpenCLIP (PE Core image + text) and timm PE Core, Spatial, Lang (ViT only) weights. NOTE: These weights do not work with original modeling code. • 19 items • Updated Sep 19, 2025 • 6

upvoted a paper 6 months ago

RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations

Paper • 2412.19628 • Published Dec 27, 2024 • 2

upvoted a collection 6 months ago

RecNeXt

37 items • Updated Aug 1, 2025 • 2