Software: Open Source Contributions

Co-developed the LLM-Culture library within the Flowers team. This software enables simulating networks composed of LLMs agents, that can generate text over multiple generations based on their neighbors input, personnality and task. The project also provides tools for analyzing the resulting text dynamics and offers an user-friendly web interface, making it accessible to non-programmers.

Developed a turorial for parallelized hyper parameter search using Optuna in the ReservoirPy machine learning library. The tutorial covers sequential and parallelized hyperparameter search on local machines using the joblib package. It also demonstrates how to scale up this process by utilizing Slurm files to parallelize the search on remote clusters of CPUs.

I helped creating this Hugging Face space for KanRL, a project studying the combination of Reinforcement Learning and Kolmogorov-Arnold Networks (KANs). I also led experiments to compare the performance of simple Policy Gradient and PPO algorithms using both KANs and MLPs.

Fixed several issues on the Stable-Baselines3 and Stable-Baselines3-Contrib Reinforcement Learning Libraries.