collaborators

6 papers

physics.comp-ph2025

Refining Machine Learning Potentials through Thermodynamic Theory of Phase Transitions

Paul Fuchs, Julija Zavadlav

Foundational Machine Learning Potentials can resolve the accuracy and transferability limitations of classical force fields. They enable microscopic insights into material behavior…

physics.chem-ph2025

Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentials

Weilong Chen, Franz Görlich, Paul Fuchs +1

Coarse-graining (CG) enables molecular dynamics (MD) simulations of larger systems and longer timescales that are otherwise infeasible with atomistic models. Machine learning poten…

physics.chem-ph2025

Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration

Paul Fuchs, Michał Sanocki, Julija Zavadlav

Graph Neural Network (GNN) potentials relying on chemical locality offer near-quantum mechanical accuracy at significantly reduced computational costs. Message-passing GNNs model i…

physics.comp-ph2025

chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations

Paul Fuchs, Weilong Chen, Stephan Thaler +1

Machine learning potentials (MLPs) have advanced rapidly and show great promise to transform molecular dynamics (MD) simulations. However, most existing software tools are tied to…

stat.CO2025

JaxSGMC: Modular stochastic gradient MCMC in JAX

Stephan Thaler, Paul Fuchs, Ana Cukarska +1

We present JaxSGMC, an application-agnostic library for stochastic gradient Markov chain Monte Carlo (SG-MCMC) in JAX. SG-MCMC schemes are uncertainty quantification (UQ) methods t…

physics.chem-ph2025

chemtrain: Learning Deep Potential Models via Automatic Differentiation and Statistical Physics

Paul Fuchs, Stephan Thaler, Sebastien Röcken +1

Neural Networks (NNs) are effective models for refining the accuracy of molecular dynamics, opening up new fields of application. Typically trained bottom-up, atomistic NN potentia…