Go directly to page contentent
TEAM LADE
Yuri Gardinazzi
Researcher at Laboratory of Data Engineering

I am a PhD student in Applied Data Science and Artificial Intelligence with a background in Computer Science, collaborating with the LADE group under the supervision of Matteo Biagetti. My research focuses on Large Language Models and biological systems, exploring them through Topological Data Analysis, a rapidly evolving field of applied mathematics. During a recent visiting research period at the Inria Centre at Université Côte d’Azur, I worked with the Datashape team on the development of diffusion models conditioned by topological descriptors..

Research Interests
  • Topological Data Analysis
  • Interpretability of AI Models
  • Complex Systems
Experience & Education
  • Visiting period of 6 months at Inria Centre at Université Côte d’Azur and worked with Mathieu Carrière (Jan 2025 – Apr 2026)
  • PhD Student in Applied Data Science and Artificial Intelligence at University of Trieste (Nov 2023 – Oct 2026)
  • Master and Bachelor degree in Computer Science at University of Modena and Reggio Emilia
Latest Publications
09/06/2026
Decoding the Grammar of Protein-Protein Interaction Interfaces with Multimodal Representations
Abstract Protein-protein interactions govern essential cellular processes, making the identification of interacting sites a central…
Go to the news Decoding the Grammar of Protein-Protein Interaction Interfaces with Multimodal Representations
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…
Go to the news Zigzag Persistence of Neural Responses to Time-Varying Stimuli
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…
Go to the news Zigzag Persistence of Large Language Models Representations
17/01/2025
The Geometry of Tokens in Internal Representations of Large Language Models
Abstract We investigate the relationship between the geometry of token embeddings and their role in…
Go to the news The Geometry of Tokens in Internal Representations of Large Language Models
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.…
Go to the news Persistent Topological Features in Large Language Models