Oliver T. Unke

21 papers A* 3Journal 18
YearRankTypeTitle / Venue / Authors
2026 J jnl
Characterizing High-Capacity Janus Aminobenzene-Graphene Anode for Sodium-Ion Batteries with Machine Learning.
CoRR
Claudia Islas-Vargas, L. Ricardo Montoya, Carlos A. Vital-José, Oliver T. Unke, Klaus-Robert Müller, Huziel E. Sauceda
2026 J jnl
Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics.
CoRR
Winfried Ripken, Michael Plainer, Gregor Lied, J. Thorben Frank, Oliver T. Unke, Stefan Chmiela, Frank Noé, Klaus-Robert Müller
2025 J jnl
Control Variate Score Matching for Diffusion Models.
CoRR
Khaled Kahouli, Romuald Elie, Klaus-Robert Müller, Quentin Berthet, Oliver T. Unke, Arnaud Doucet
2025 J jnl
Enhancing Diffusion Models Efficiency by Disentangling Total-Variance and Signal-to-Noise Ratio.
CoRR
Khaled Kahouli, Winfried Ripken, Stefan Gugler, Oliver T. Unke, Klaus-Robert Müller, Shinichi Nakajima
2025 J jnl
How simple can you go? An off-the-shelf transformer approach to molecular dynamics.
CoRR
Max Eissler, Tim Korjakow, Stefan Ganscha, Oliver T. Unke, Klaus-Robert Müller, Stefan Gugler
2025 J jnl
Sampling 3D Molecular Conformers with Diffusion Transformers.
CoRR
J. Thorben Frank, Winfried Ripken, Gregor Lied, Klaus-Robert Müller, Oliver T. Unke, Stefan Chmiela
2024 J jnl
Complete and Efficient Covariants for 3D Point Configurations with Application to Learning Molecular Quantum Properties.
CoRR
Hartmut Maennel, Oliver T. Unke, Klaus-Robert Müller
2024 J jnl
E3x: E(3)-Equivariant Deep Learning Made Easy.
CoRR
Oliver T. Unke, Hartmut Maennel
2024 J jnl
Euclidean Fast Attention: Machine Learning Global Atomic Representations at Linear Cost.
CoRR
J. Thorben Frank, Stefan Chmiela, Klaus-Robert Müller, Oliver T. Unke
2023 J jnl
From Peptides to Nanostructures: A Euclidean Transformer for Fast and Stable Machine Learned Force Fields.
CoRR
J. Thorben Frank, Oliver T. Unke, Klaus-Robert Müller, Stefan Chmiela
2022 J jnl
Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations.
CoRR
Oliver T. Unke, Martin Stöhr, Stefan Ganscha, Thomas Unterthiner, Hartmut Maennel, Sergii Kashubin, Daniel Ahlin, Michael Gastegger, Leonardo Medrano Sandonas, Alexandre Tkatchenko, Klaus-Robert Müller
2022 J jnl
Automatic Identification of Chemical Moieties.
CoRR
Jonas Lederer, Michael Gastegger, Kristof T. Schütt, Michael Kampffmeyer, Klaus-Robert Müller, Oliver T. Unke
2022 J jnl
So3krates - Self-attention for higher-order geometric interactions on arbitrary length-scales.
CoRR
J. Thorben Frank, Oliver T. Unke, Klaus-Robert Müller
2022 A* conf
So3krates: Equivariant attention for interactions on arbitrary length-scales in molecular systems.
NeurIPS
J. Thorben Frank, Oliver T. Unke, Klaus-Robert Müller
2021 A* conf
Equivariant message passing for the prediction of tensorial properties and molecular spectra.
ICML
Kristof Schütt, Oliver T. Unke, Michael Gastegger
2021 J jnl
Equivariant message passing for the prediction of tensorial properties and molecular spectra.
CoRR
Kristof T. Schütt, Oliver T. Unke, Michael Gastegger
2021 A* conf
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities.
NeurIPS
Oliver T. Unke, Mihail Bogojeski, Michael Gastegger, Mario Geiger, Tess E. Smidt, Klaus-Robert Müller
2021 J jnl
SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects.
CoRR
Oliver T. Unke, Stefan Chmiela, Michael Gastegger, Kristof T. Schütt, Huziel E. Sauceda, Klaus-Robert Müller
2020 J jnl
High-dimensional potential energy surfaces for molecular simulations: from empiricism to machine learning.
Mach. Learn. Sci. Technol.
Oliver T. Unke, Debasish Koner, Sarbani Patra, Silvan Käser, Markus Meuwly
2017 J jnl
Migration of small ligands in globins: Xe diffusion in truncated hemoglobin N.
PLoS Comput. Biol.
Polydefkis Diamantis, Oliver T. Unke, Markus Meuwly
2017 J jnl
Toolkit for the Construction of Reproducing Kernel-Based Representations of Data: Application to Multidimensional Potential Energy Surfaces.
J. Chem. Inf. Model.
Oliver T. Unke, Markus Meuwly