Dr. Alessandro Caruso

Theoretical Chemist | Machine Learning Researcher

Pioneering the intersection of machine learning and molecular physics. Developing cutting-edge graph neural networks to unlock the secrets of biomolecular interactions with chemical accuracy.

View Research → Collaborate

Recent Publications

Extending the RANGE of Graph Neural Networks: Relaying Attention Nodes for Global Encoding

arXiv preprint, 2025 | Caruso A., et al.

RANGE is a model-agnostic framework that employs an attention-based aggregation-broadcast mechanism to capture long-range interactions in graph-like structures.

Read Paper Code

Consistent density functional theory-based description of ion hydration through density-corrected many-body representations

J. Chem. Phys., 2023 | Palos E., et al.

We demonstrate that density-corrected SCAN predicts n-body and interaction energies of hydrated ions with an accuracy approaching coupled cluster theory.

Read Paper

A “short blanket” dilemma for a state-of-the-art neural network potential for water: Reproducing experimental properties or the physics of the underlying many-body interactions?

J. Chem. Phys., 2023 | Zhai Y., et al.

DeePMD-based DNN potentials are not able to correctly represent many-body interactions. This explains their limited ability to predict properties for state points that are not explicitly included in the training process.

Read Paper Data

Curriculum Vitae

Education

Ph.D. in Theoretical Chemistry
University of California, San Diego (2018-2023)

M.S. in Physical Chemistry
Sapienza, University of Rome (2016-2018)

B.S. in Chemistry
Sapienza, University of Rome (2013-2016)

Current Position

Postdoctoral Researcher
Department of Theoretical Biophysics
Freie Universität Berlin (2023-Present)

Research Interests

machine-learning force fields, equivariant message-passing, long-range interactions, density functional theory, molecular dynamics

Download Full CV (PDF)