Privacy Preserving AI Hackathon (Zama, Hugging Face, Entrepreneur First)

AI & ML interests

None defined yet.

Recent Activity

Xmaster6y  authored a paper 9 days ago

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning

Sckathach  authored a paper 7 months ago

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

benkoska  authored a paper 10 months ago

Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model

View all activity

Team members 60