Scholar
François Lanusse
Google Scholar ID: fRDCooIAAAAJ
CNRS Researcher
Citations & Impact
Citations
4,155
H-index
33
i10-index
61
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published multiple papers at NeurIPS 2025 main conference and AI4Science and ML for physical sciences workshops; released the first version of the Multimodal Universe dataset, the first “web scale” dataset of astronomical data for foundation model training; several papers accepted at the 2023 ICML ML4Astro Workshop; jax-cosmo paper published on arxiv; led various research projects, including using generative modeling and autodiff to measure cosmic shear from space.
Research Experience
- Between 2023-2024, he was an Associate Research Scientist at the Flatiron Institute in New York City, part of the inaugural Polymathic AI research group; currently, he is an active member of both the LSST Dark Energy Science Collaboration (LSST DESC) and the LSST Informatics & Statistics Science Collaboration (LSST ISSC).
Education
- Before his CNRS position, he was a postdoctoral fellow at the Berkeley Center for Cosmological Physics (BCCP) and the Foundation of Data Analysis (FODA) institute at UC Berkeley, working with Prof. Uroš Seljak. Prior to that, he was a postdoctoral researcher in the McWilliams Center for Cosmology at Carnegie Mellon University, where he worked with Prof. Rachel Mandelbaum on weak gravitational lensing measurements and systematics, and interacted with both Statistics and Machine Learning departments while at CMU.
Background
- CNRS researcher working at the intersection between Deep Learning, Statistical Modeling, and Observational Cosmology. Particularly interested in combining tools and methodologies from Machine Learning (automatic differentiation, generative AI) with physical modeling for the analysis of Cosmological Surveys.
Miscellany
- Personal interests not mentioned
Co-authors