5 citations · 10 across the 13 of their papers we have counts for
3 papers · 1 filter
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…