Yoann Poupart's picture

9 9 8

Yoann Poupart

Xmaster6y

·

https://yp-edu.github.io/

Xmaster6y

AI & ML interests

AI Safety | Interpretability | LLM | RL

Recent Activity

liked a Space 4 days ago

dlouapre/eiffel-tower-llama

upvoted a paper about 2 months ago

FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents

authored a paper 2 months ago

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning

View all activity

Organizations

authored a paper 2 months ago

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning

Paper • 2502.00726 • Published Feb 2 • 1

authored a paper over 1 year ago

Contrastive Sparse Autoencoders for Interpreting Planning of Chess-Playing Agents

Paper • 2406.04028 • Published Jun 6, 2024 • 2