output
20152026
most citedAn asymptotic shape theorem for additive random linear growth models

3 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions

12 papers

cs.LG2026

Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs

Léo Nicollier, Enric Meinhardt-Llopis, Marc Pic +2

Recent Joint-Embedding Predictive Architectures (JEPAs) prevent representation collapse by constraining learned representations to follow a prescribed target distribution, such as…

cs.LG2026

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…

cs.LG2026

Unbiased Open World Regularization for Fair Self-Supervised Learning

Léo Nicollier, L{é}o Nicollier, Marc Pic +4

Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to spurious correlations. Many anti-collapse…

cs.LG2026

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…

cs.LG2026

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…

math.OC2026

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…

math.PR2026

The Contact Process Can Survive on a Slightly Subcritical Dynamical Percolation Cluster

Aurelia Deshayes, Régine Marchand

The contact process on dynamic edges (CPDE) is a contact process evolving on a dynamic environment given by a dynamical percolation on the edges of Z d\,: each edge updates its sta…

math.PR2025

The Rightmost Particle of the Contact Process on Dynamic Random Environments

Isabella Alvarenga, Aurelia Deshayes

We study the behaviour of the rightmost occupied site in two models: the Spont process and the contact process with inherited sterility, in dimension 1. Both can be viewed as conta…

cs.CV2025

Blur2seq: Blind Deblurring and Camera Trajectory Estimation from a Single Camera Motion-blurred Image

Guillermo Carbajal, Andrés Almansa, Pablo Musé

Motion blur caused by camera shake, particularly under large or rotational movements, remains a major challenge in image restoration. We propose a deep learning framework that join…

math.GT2023★ 1 cited

Anosov representations acting on homogeneous spaces: domains of discontinuity

León Carvajales, Florian Stecker

We construct open domains of discontinuity for Anosov representations acting on some homogeneous spaces, including (pseudo-Riemannian) symmetric spaces. This generalizes work of Ka…

math.QA2023

Slack Hopf Monads

Alain Bruguières, Mariana Haim, Ignacio López Franco

Hopf monads generalise Hopf algebras. They clarify several aspects of the theory of Hopf algebras and capture several related structures such as weak Hopf algebras and Hopf algebro…

math.PR2015★ 3 cited

An asymptotic shape theorem for additive random linear growth models

Aurelia Deshayes, Pierrick Siest

In this paper, we define a class of additive random growth models whose growth is at least and at most linear and prove an asymptotic shape theorem for these models. This proof gen…