Physics-informed machine learning potential for nanoparticle self-assembly: 3000x faster than explicit simulation. Permutationally invariant polynomials fitted to CG MD potentials of mean force. Reproduces 1D strings, 2D sheets, 3D aggregates. npj Computational Materials 2023.

Correlated, nonperturbative electronic structure calculations based on diagrammatic techniques: the random-phase approximation and related higher-level theories

Thermodynamics of organic molecular crystals using surrogate models for the correlated electronic energy.