collaborators

6 papers

physics.chem-ph2026

ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table

Jacob W. Toney, Samir Darouich, Yiran Wang +3

Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined t…

physics.chem-ph2026

How to Train a Shallow Ensemble

Moritz Schäfer, Matthias Kellner, Johannes Kästner +1

Shallow ensembles provide a convenient strategy for uncertainty quantification in machine learning interatomic potentials, that is computationally efficient because the different e…

astro-ph.GA2026

Atom Addition Formation of Thionylimide (HNSO) on Interstellar Dust Grains: Chemical routes requiring oxygen and nitrogen atom surface diffusion

Juan Carlos del Valle, Miguel Sanz-Novo, Johannes Kästner +4

We investigate the formation of the recently detected HNSO molecule using quantum chemical calculations on ices and astrochemical models in tandem. Our results indicate that HNSO i…

physics.chem-ph2026

Enhanced Representation-Based Sampling for the Efficient Generation of Datasets for Machine-Learned Interatomic Potentials

Moritz René Schäfer, Johannes Kästner

In this work, we present Enhanced Representation-Based Sampling (ERBS), a novel enhanced sampling method designed to generate structurally diverse training datasets for machine-lea…

physics.chem-ph2025

Adaptive Transition State Refinement with Learned Equilibrium Flows

Samir Darouich, Vinh Tong, Tanja Bien +2

Identifying transition states (TSs), the high-energy configurations that molecules pass through during chemical reactions, is essential for understanding and designing chemical pro…

physics.chem-ph2025

Apax: A Flexible and Performant Framework For The Development of Machine-Learned Interatomic Potentials

Moritz René Schäfer, Nico Segreto, Fabian Zills +2

We introduce Atomistic learned potentials in JAX (apax), a flexible and efficient open source software package for training and inference of machine-learned interatomic potentials.…