Alessandro Benfenati — accepted AI-conference papers

2025

Unveiling Transformer Perception by Exploring Input Manifolds

Alessandro Benfenati, Alfio Ferrara, Alessio Marta, Davide Riva, Elisabetta Rocchetti

NeurIPS 2025poster

This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical theory which describes the internal layers of a Transformer architecture as sequential deformations of the input manifold.…

Cited by 0 Source ↗Scholar ↗

2018

A Nonconvex Variational Approach for Robust Graphical Lasso

Alessandro Benfenati, Emilie Chouzenoux, Jean-Christophe Pesquet

ICASSP 2018accepted

In recent years, there has been a growing interest in problems in graph estimation and model selection, which all share very similar matrix variational formulations, the most popular one being probably GLASSO. Unfortunately, the standard GLASSO formulation does not take into account noise corrupting…

Cited by 0 Source ↗Scholar ↗