CV

Education

• Ph.D in Artificial Intelligence, University of Pisa, 2027 (expected)
• M.S. in Mathematics, University of Pisa, 2022
• Master in Mathematics, Scuola Normale Superiore, 2022
• B.S. in Mathematics, University of Pisa, 2020

Work experience

• 2022-2023: Data Scientist
  • Electra Vechicles inc.
  • Machine Learning models for fault prediction in electric batteries and smart charging.

Awards

• Bronze Medal at International Physics Olympiad (IPhO) 2017
• Gold Medal at the Italian Mathematics Olympiad (ItaMO) 2017
• Gold Medal at the Italian Physics Olympiad 2017
• Silver Medal at the Italian Mathematics Olympiad (ItaMO) 2016
• Bronze Medal at the Italian Physics Olympiad 2016
• Bronze Medal at the Italian Mathematics Olympiad (ItaMO) 2015

Publications

Continual Learning of Physical Systems via Derivative Distillation

C. Gentili, A. Trenta, A. Cossu, and D. Bacciu., (2026). "Continual Learning of Physical Systems via Derivative Distillation" Continual Adaptation at Scale: Towards Sustainable AI Workshop at ICML 2026.

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Hoang T., Trenta A.*, Gravina A., Freymuth N., Becker P., Bacciu D., Neumann G., (2026). "Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics" International Conference on Learning Representations (ICLR).

ComPhy: Composing Physical Models with end-to-end Alignment

Trenta A., Cossu A., Bacciu D., (2026). "ComPhy: Composing Physical Models with end-to-end Alignment" International Conference on Learning Representations (ICLR).

Learning and Transferring Physical Models Trhough Derivatives

Trenta A., Cossu A., Bacciu D., (2026). "Learning and Transferring Physical Models through Derivatives" Transactions on Machine Learning Research (TMLR).

SONAR: Long-Range Graph Propagation through Information Waves

Trenta A.*, Gravina A.*, Bacciu D., (2025). "SONAR: Long-Range Graph Propagation through Information Waves" Neural Information Processing Systems (NeurIPS).

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

Heilig S.*, Gravina A.*, Trenta A., Gallicchio C., Bacciu D., (2025). "Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks." International Conference on Learning Representations (ICLR).