5 papers
RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment
Chao Wang, Giulio Franzese, Alessandro Finamore +1
Rectified Flow (RF) models trained with a Flow matching framework have achieved state-of-the-art performance on Text-to-Image (T2I) conditional generation. Yet, multiple benchmarks…
Learning to Match Unpaired Data with Minimum Entropy Coupling
Mustapha Bounoua, Giulio Franzese, Pietro Michiardi
Multimodal data is a precious asset enabling a variety of downstream tasks in machine learning. However, real-world data collected across different modalities is often not paired,…
INFO-SEDD: Continuous Time Markov Chains as Scalable Information Metrics Estimators
Alberto Foresti, Giulio Franzese, Pietro Michiardi
Information-theoretic quantities play a crucial role in understanding non-linear relationships between random variables and are widely used across scientific disciplines. However,…
In Praise of Stubbornness: An Empirical Case for Cognitive-Dissonance Aware Continual Update of Knowledge in LLMs
Simone Clemente, Zied Ben Houidi, Alexis Huet +3
Through systematic empirical investigation, we uncover a fundamental and concerning property of Large Language Models: while they can safely learn facts that don't contradict their…
Latent Abstractions in Generative Diffusion Models
Giulio Franzese, Mattia Martini, Giulio Corallo +2
In this work we study how diffusion-based generative models produce high-dimensional data, such as an image, by implicitly relying on a manifestation of a low-dimensional set of la…