I am an engineering student in Computer Science and Artificial Intelligence at INSA Rouen Normandy and an incoming Master’s student in Machine Learning for Artificial Intelligence at the University of Rouen Normandy.

My current internships apply deep learning to different domains: at InterDigital, I work on methods for next-generation video compression, with emphasis on VVC (H.266) in-loop filtering and decoder-side filter selection; at Enedis, I work on generative modeling and large-scale pipelines for high-frequency electricity-grid time-series simulation.

Recent projects include Hack the World(s), where our team was a finalist at a 24-hour hackathon on JEPAs and world models sponsored by Yann LeCun. We built a joint-embedding EEG SSL system with Riemannian latent analysis showing structure in SPD covariance representations. Other recent projects include Opportunistic Target Selection, a lightweight wrapper for query-efficient score-based black-box adversarial attacks accepted at CAp 2026, and DashVMC, an independent research project on real-time discrete world model control in Geometry Dash.

I am seeking a six-month final-year research internship in deep learning starting in 2027.

Research interests

• Deep Learning
• Representation Learning
• Self-Supervised Learning
• World Models
• Model-Based Reinforcement Learning and Planning