Marco Pacini
PhD Candidate at University of Trento & Fondazione Bruno Kessler
My research focuses on the fundamental principles of Geometric Deep Learning and Equivariant Machine Learning.
Some of my research interests include the constructive characterization of equivariant models, as well as their expressivity and approximation capabilities.
News
| Sep 18, 2025 | On Universality Classes of Equivariant Networks was accepted to NeurIPS 2025 as a Spotlight. |
|---|---|
| Jun 06, 2025 | New preprint of “On Universality Classes of Equivariant Networks” is out on ArXiv now! |
| Feb 11, 2025 | Separation Power of Equivariant Neural Networks has been accepted to ICLR 2025! |
| Jun 14, 2024 | New preprint of “Separation Power of Equivariant Neural Networks” is out on ArXiv now! |
| Jan 15, 2024 | A Characterization Theorem for Equivariant Networks with Point-wise Activations was accepted at ICLR 2024. |
