1 17 4

Cyril

cyrilzakka

https://cyrilzakka.github.io

AI & ML interests

Multimodal models for clinical medicine and surgery

Recent Activity

upvoted an article 4 days ago

You could have designed state of the art positional encoding

upvoted an article 12 days ago

Common AI Model Formats

upvoted a paper 15 days ago

Qwen2.5-VL Technical Report

View all activity

Organizations

cyrilzakka's activity

upvoted an article 4 days ago

Article

You could have designed state of the art positional encoding

Nov 25, 2024

• 180

upvoted an article 12 days ago

Article

Common AI Model Formats

•

12 days ago

• 27

upvoted a paper 15 days ago

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published 20 days ago • 158

upvoted a paper 18 days ago

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published 19 days ago • 128

upvoted an article 18 days ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

19 days ago

• 199

upvoted an article 29 days ago

Article

Open R1: Update #2

and 6 others •

29 days ago

• 199

upvoted a paper about 1 month ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 201

upvoted an article about 1 month ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.15k

upvoted a paper about 1 month ago

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published Feb 3 • 55

upvoted a paper 2 months ago

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

Paper • 2501.04519 • Published Jan 8 • 260

upvoted 3 papers 3 months ago

Qwen2.5 Technical Report

Paper • 2412.15115 • Published Dec 19, 2024 • 351

Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusion

Paper • 2412.04424 • Published Dec 5, 2024 • 61

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 129

upvoted 2 collections 3 months ago

PaliGemma 2 Release

Collection

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 32 items • Updated 3 days ago • 145

Deepseek Papers

Collection

Deepseek papers collection • 18 items • Updated 21 days ago • 166

upvoted a paper 5 months ago

EchoPrime: A Multi-Video View-Informed Vision-Language Model for Comprehensive Echocardiography Interpretation

Paper • 2410.09704 • Published Oct 13, 2024 • 13