Stefano Fiorini

Postdoctoral Researcher at Istituto Italiano di Tecnologia

About Me

Stefano Fiorini

I am Stefano, a Postdoctoral Researcher at the Istituto Italiano di Tecnologia and a visiting researcher at the University of Cambridge in the group led by Professor Pietro LiΓ². My journey in academia has been fueled by a passion for pushing the boundaries of knowledge and applying advanced computational methods to solve real-world problems.

I earned my Ph.D. in Computer Science from the University of Milano-Bicocca in 2023, building a robust interdisciplinary foundation in machine learning, graph theory, and applications from computational chemistry to smart mobility. My academic path includes impactful experiences such as an internship at Nokia Bell Labs (2021) and a research visit at the Mathematics Department at the University of Southampton (2022).

My research interests span Graph Neural Networks, Hypergraph Neural Networks, Computer Vision, Computational Chemistry, Diffusion Models, and Smart Mobility. I thrive on continuous learning and value collaboration with diverse research groups to explore innovative ideas.

Outside of academia, I enjoy hiking, skiing, reading, and traveling to different countries. These activities inspire creative thinking and provide a refreshing balance to my professional pursuits.

Previous Experiences

Research Interests

Links

πŸ“š Google Scholar
πŸ’Ό LinkedIn
πŸ§‘β€πŸ’» GitHub
πŸ“„ Download my CV

Selected Publications

2025
S. Fiorini, G. M. Bovolenta, S. Coniglio, M. Ciavotta, M. Parrinello, A. Del Bue. DLGNET: Hyperedge Classification through Directed Line Graphs for Chemical Reaction.
2024
S. Fiorini, S. Coniglio, M. Ciavotta, A. Del Bue. Let There be Direction in Hypergraph Neural Networks. Transactions on Machine Learning Research (TMLR).
G. Scarpellini1, S. Fiorini1, F. Giuliari1, P. Morerio, A. Del Bue. DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly. CVPR 2024.
S. Fiorini, S. Coniglio, M. Ciavotta, E. Messina. Graph Learning in 4D: a Quaternion-valued Laplacian to Enhance Spectral GCNs. AAAI 2024.
F. Giuliari, G. Scarpellini, S. Fiorini, S. James, P. Morerio, Y. Wang, A. Del Bue. Positional Diffusion: Graph-based Diffusion Models for Set Ordering. Pattern Recognition Letters 186 (2024).
2023
S. Fiorini, S. Coniglio, M. Ciavotta, E. Messina. SigMaNet: One Laplacian to Rule Them All. AAAI 2023.

1 Equal contribution