Nicolò Lazzaro

The paper develops a generative framework to synthesize missing modalities in multimodal datasets, validated on cancer data, showing it can maintain predictive model performance on incomplete profiles.

This study evaluates generative models for transcriptomics data using statistical distances to assess their performance and convergence.

This paper introduces Signature Distance, a statistical distance that improves upon energy distance for comparing empirical distributions in high-dimensional biological data, showing greater sensitivity to density changes and enabling model-free data expansion.