Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Published in top venues including Science, Journal of Advances in Earth Modeling Systems, Geoscientific Model Development, Physical Review Materials, J. Chem. Phys., ICLR, NeurIPS, and ICCC.
Developed and open-sourced multiple PyTorch implementations: multi-layer quasi-geostrophic solvers, neural style transfer (STROTSS), 3D solid-harmonic scattering transforms, Angular Fourier Series descriptors, etc.
Co-developed Kymatio, an open-source Python package for scattering transforms, published in Journal of Machine Learning Research (2020).
Presented research at the Stochastic Transport in Upper Ocean Dynamics Workshop, Imperial College London (2023).
Delivered a guest talk on AI and Art at the 'P versus NP' event at Futurium Museum, Berlin, featuring a live demo of AI-generated portraits drawn by a robotic arm.
Research Experience
2024–2025: Researcher on LLM/VLM-based autonomous software agents at H Company, Paris.
2024: Postdoc on hybrid physics-learning ocean modeling with the ANGE team at INRIA Paris.
2021–2023: Postdoc on stochastic modeling and data assimilation for oceanic flows with the ODYSSEY team at INRIA Rennes.
2022: Taught Statistics and Probability to first-year computer science students at ENS Rennes.
Led practical sessions (TPs) on Fundamentals of Deep Learning with accompanying slides.