collaborators

13 papers

physics.ao-ph2026

Optimal sensor placement for the reconstruction of ocean states using differentiable Gumbel-Softmax sampling operator

Oscar Chapron, Ronan Fablet, Yann Stéphan

Accurately reconstructing and forecasting ocean fields from sparse observations is critical for both operational and scientific purposes. Optimizing sensor placement to maximize re…

eess.SP2026

Majorization-Minimization Networks for Inverse Problems: An Application to EEG Imaging

Le Minh Triet Tran, Sarah Reynaud, Ronan Fablet +3

Inverse problems are often ill-posed and require optimization schemes with strong stability and convergence guarantees. While learning-based approaches such as deep unrolling and m…

cs.LG2026

Take It or Leave It: Intent-Controlled Partial Optimal Transport

Salil Parth Tripathi, Bertrand Chapron, Fabrice Collard +2

While optimal transport (OT) enforces a rigid constraint by requiring two measures to be matched exactly, partial optimal transport relaxes this requirement by allowing mass to rem…

physics.ao-ph2026

Impact of geophysical fields on Deep Learning-based Lagrangian drift simulations

Daria Botvynko, Carlos Granero-Belinchon, Simon Van Gennip +2

We assess the influence of different Eulerian geophysical input fields on Lagrangian drift simulations using DriftNet, a learning-based method designed to simulate Lagrangian drift…

cs.LG2026

Static and auto-regressive neural emulation of phytoplankton biomass dynamics from physical predictors in the global ocean

Mahima Lakra, Ronan Fablet, Lucas Drumetz +2

Phytoplankton is the basis of marine food webs, driving both ecological processes and global biogeochemical cycles. Despite their ecological and climatic significance, accurately s…

cs.LG2026

Discovering Data Manifold Geometry via Non-Contracting Flows

David Vigouroux, Lucas Drumetz, Ronan Fablet +1

We introduce an unsupervised approach for constructing a global reference system by learning, in the ambient space, vector fields that span the tangent spaces of an unknown data ma…