2 papers
q-bio.NC2025
Shaping manifolds in equivariant recurrent neural networks
Arianna Di Bernardo, Adrian Valente, Francesca Mastrogiuseppe +1
Recordings of increasingly large neural populations have revealed that the firing of individual neurons is highly coordinated. When viewed in the space of all possible patterns, th…
cs.LG2025
What's Inside Your Diffusion Model? A Score-Based Riemannian Metric to Explore the Data Manifold
Simone Azeglio, Arianna Di Bernardo
Recent advances in diffusion models have demonstrated their remarkable ability to capture complex image distributions, but the geometric properties of the learned data manifold rem…