5 citations · 10 across the 13 of their papers we have counts for
13 papers
Harmonic morphisms and dynamical invariants in network renormalization
Francesco Maria Guadagnuolo, Marco Nurisso, Federica Galluzzi +2
Renormalization of complex networks requires principled criteria for assessing whether a coarse-graining preserves dynamical content. We prove that discrete harmonic morphisms -- s…
The Geometry of Representational Failures in Vision Language Models
Daniele Savietto, Declan Campbell, André Panisson +4
Vision-Language Models (VLMs) exhibit puzzling failures in multi-object visual tasks, such as hallucinating non-existent elements or failing to identify the most similar objects am…
Topology and Geometry of the Learning Space of ReLU Networks: Connectivity and Singularities
Marco Nurisso, Pierrick Leroy, Giovanni Petri +1
Understanding the properties of the parameter space in feed-forward ReLU networks is critical for effectively analyzing and guiding training dynamics. After initialization, trainin…
From Nodes to Edges: Edge-Based Laplacians for Brain Signal Processing
Andrea Santoro, Marco Nurisso, Giovanni Petri
Traditional graph signal processing (GSP) methods applied to brain networks focus on signals defined on the nodes. Thus, they are unable to capture potentially important dynamics o…
SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
Enrico Cassano, Riccardo Renzulli, Marco Nurisso +3
Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computatio…
Attributes Shape the Embedding Space of Face Recognition Models
Pierrick Leroy, Antonio Mastropietro, Marco Nurisso +1
Face Recognition (FR) tasks have made significant progress with the advent of Deep Neural Networks, particularly through margin-based triplet losses that embed facial images into h…
Bound by semanticity: universal laws governing the generalization-identification tradeoff
Marco Nurisso, Jesseba Fernando, Raj Deshpande +9
Intelligent systems must deploy internal representations that are simultaneously structured -- to support broad generalization -- and selective -- to preserve input identity. We ex…
Topological obstruction to the training of shallow ReLU neural networks
Marco Nurisso, Pierrick Leroy, Francesco Vaccarino
Studying the interplay between the geometry of the loss landscape and the optimization trajectories of simple neural networks is a fundamental step for understanding their behavior…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
Higher-order Laplacian Renormalization
Marco Nurisso, Marta Morandini, Maxime Lucas +3
We propose a cross-order Laplacian renormalization group (X-LRG) scheme for arbitrary higher-order networks. The renormalization group is a pillar of the theory of scaling, scale-i…
Network-based kinetic models: Emergence of a statistical description of the graph topology
Marco Nurisso, Matteo Raviola, Andrea Tosin
In this paper, we propose a novel approach that employs kinetic equations to describe the collective dynamics emerging from graph-mediated pairwise interactions in multi-agent syst…
A unified framework for Simplicial Kuramoto models
Marco Nurisso, Alexis Arnaudon, Maxime Lucas +4
Simplicial Kuramoto models have emerged as a diverse and intriguing class of models describing oscillators on simplices rather than nodes. In this paper, we present a unified frame…
Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections
Simone Azeglio, Simone Poetto, Luca Savant Aira +1
Computational models of vision have traditionally been developed in a bottom-up fashion, by hierarchically composing a series of straightforward operations - i.e. convolution and p…