15 citations
- Universidade Federal FluminenseBR9 papers
- Institut Franco-Uruguayen des Mathématiques et InteractionsUY6 papers
- Sustainable Sciences InstituteUS3 papers
- Universidade Estadual de Campinas (UNICAMP)BR3 papers
- Universidade Federal do Rio de JaneiroBR3 papers
- Instituto Federal do Espírito SantoBR2 papers
- Instituto Federal do Rio de JaneiroBR2 papers
- Muncipal de Bom Jesus do ItabapoanaBR2 papers
- Universidade Federal de Campina GrandeBR2 papers
- Association of the Technological Integrated Systems LaboratoryBR1 paper
- Centro Brasileiro de Pesquisas FísicasBR1 paper
- Concerned Black Men NationalUS1 paper
28 papers
Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO___ Retrieval, and Application to Interferometric Sensing
Jordan Lontsi Tedongmo, Yann Ferrec, Laurence Croizé +3
Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates spaceborne measu…
On the Optimized Use of Non-Orthonormality Constraints for the Quasi-Static INS Alignment of Autonomous Underwater and Surface Vehicles
Carlos Renato C. Durao, Felipe O. Silva, Itzik Klein +4
Inertial navigation systems are specialized navigation apparatuses that equip almost all autonomous underwater and surface vehicles. They require precise initial alignment, i.e., d…
Unbiased Open World Regularization for Fair Self-Supervised Learning
L{é}o Nicollier, Marc Pic, Pablo Mus{é} +2
Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. T…
Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere
Léo Nicollier, Enric Meinhardt-Llopis, Max Dunitz +3
In Self-Supervised Learning (SSL), preventing representation collapse by explicitly enforcing a uniform distribution on the unit hypersphere has proven to be effective. However, cu…
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
L{é}o Nicollier, Léo Nicollier, Max Dunitz +5
A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified i…
Mollified Christoffel-Darboux Kernels and Density Recovery on Varieties
Leandro Bentancur, Didier Henrion, Mauricio Velasco
We introduce mollified Christoffel-Darboux (CD) kernels on varieties, a systematic regularization of the classical CD kernel associated with a probability measure on a compact doma…