Go directly to page contentent
Menu
TEAM LADE

Matteo Biagetti

Researcher at Laboratory of Data Engineering

I am a research scientist. I work on methods that uncover structure in high-dimensional data. I earned a PhD in theoretical physics and spent several years in theoretical cosmology before moving toward data-driven research. Drawing from physics and mathematics, I use topological and geometric ideas to build machine-learning tools that are easier to interpret and useful in scientific settings—from cosmology to neural representations.

Research Interests 
  • Topological Data Analysis
  • Foundations of Artificial Intelligence
  • Machine Learning for Scientific Applications
Experience & Education
  • Postdoc at SISSA, 2023
  • Postdoc at University of Amsterdam, 2020
  • PhD in Theoretical Physics at University of Geneva, 2016
  • MSc in Theoretical Physics at University of Padova, 2011
Google Scholar ORCiD
Latest Publications
01/06/2026
Zigzag Persistence of Large Language Models Representations
Abstract We analyze internal representations of large language models with zigzag persistent homology, treating depth…
01/06/2026
Zigzag Persistence of Neural Responses to Time-Varying Stimuli
Abstract We use topological data analysis to study neural population activity in the Sensorium 2023…
08/05/2026
TopoFisher: Learning Topological Summary Statistics by Maximizing Fisher Information
Abstract Persistence diagrams provide stable, interpretable summaries of geometric and topological structure and are useful…
01/05/2025
Persistent Topological Features in Large Language Models
Abstract Understanding the decision-making processes of large language models is critical given their widespread applications.…