collaborators

6 papers

stat.ML2026

Emergence of Distortions in High-Dimensional Guided Diffusion Models

Enrico Ventura, Beatrice Achilli, Luca Ambrogioni +1

Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often reduces sample diversity. Using tools from statistical physics, w…

stat.ML2026

Losing dimensions: Geometric memorization in generative diffusion

Beatrice Achilli, Enrico Ventura, Gianluigi Silvestri +5

Diffusion models power leading generative AI, but when and how they memorize training data, especially on low-dimensional manifolds, remains unclear. We find memorization emerges g…

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-nn2025

Memorization and Generalization in Generative Diffusion under the Manifold Hypothesis

Beatrice Achilli, Luca Ambrogioni, Carlo Lucibello +2

We study the memorization and generalization capabilities of Diffusion Models (DMs) when data lies on a structured latent manifold. Specifically, we consider a set of data poin…

stat.ML2025

Manifolds, Random Matrices and Spectral Gaps: The geometric phases of generative diffusion

Enrico Ventura, Beatrice Achilli, Gianluigi Silvestri +2

In this paper, we investigate the latent geometry of generative diffusion models under the manifold hypothesis. For this purpose, we analyze the spectrum of eigenvalues (and singul…

cond-mat.dis-nn2025

The Capacity of Modern Hopfield Networks under the Data Manifold Hypothesis

Beatrice Achilli, Luca Ambrogioni, Carlo Lucibello +2

We generalize the computation of the capacity of exponential Hopfield model from Lucibello and Mézard (2024) to more generic pattern ensembles, including binary patterns and patte…