Bálint Máté
I am a doctoral student in Computer Science and Physics under the supervision of François Fleuret, focusing on generative modeling, sampling methods, and free-energy estimation. During my PhD I had the great fortune to intern at Chemistry team of Meta FAIR working on organic crystal sturcture prediction; visit the group of Tristan Bereau to learn about free energies; and to spend some time AI4Science group of Microsoft Research where I played a small part in their effort to machine learn the exchange-correlation functional.

Prior to starting my PhD, I studied theoretical physics and differential geometry in Hamburg and mechanical engineering in Budapest.



Publications
Solvation Free Energies from Neural Thermodynamic Integration
2025
B. Máté, F. Fleuret and T. Bereau
The Journal of Chemical Physics 162 (12), Editor's Pick
paper | preprint | summary | bib
Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
2024
B. Máté, F. Fleuret and T. Bereau
The Journal of Physical Chemistry Letters 15 (45)
preprint | paper | summary | bib
Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows
2024
B. Máté and F. Fleuret
Machine Learning: Science and Technology 5 (4)
paper | bib
Learning Interpolations between Boltzmann Densities
2023
B. Máté and F. Fleuret
Transactions on Machine Learning Research (TMLR)
paper | summary | bib
Flowification: Everything is a Normalizing Flow
2022
B. Máté, S. Klein, T. Golling and F. Fleuret
Neural Information Processing Systems (NeurIPS)
paper | bib