3 papers
cs.LG2026
Theory of Speciation Transitions in Diffusion Models with General Class Structure
Beatrice Achilli, Marco Benedetti, Giulio Biroli +1
Diffusion Models generate data by reversing a stochastic diffusion process, progressively transforming noise into structured samples drawn from a target distribution. Recent theore…
cond-mat.dis-nn2026
Inferring Concepts from Noisy Examples in Hopfield-like Neural Networks
Marco Benedetti, Giulia Fischetti, Enzo Marinari +2
We study a variant of the pseudo-inverse learning rule for Hopfield-like Neural Networks, which allows the network to infer archetypal concepts on the basis of a limited number of…
q-bio.NC2025
Paradoxical increase of capacity due to spurious overlaps in attractor networks
Marco Benedetti, Nicolas Brunel, Enzo Marinari +1
In Hopfield-type associative memory models, memories are stored in the connectivity matrix and can be retrieved subsequently thanks to the collective dynamics of the network. In th…