Arthur Kosmala

Speculative Sampling For Faster Molecular Dynamics

Arthur Kosmala, Stephan Günnemann, Meng Gao^† and Brandon Wood^†

Accepted at ICML 2026

Spatio-Spectral Sequence Processing

Nikita Kostin, Simon Geisler, Arthur Kosmala and Stephan Günnemann

ICLR 2026 Workshop on Geometry-grounded Representation Learning

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification

Jan Schuchardt, Mihail Stoian*, Arthur Kosmala* and Stephan Günnemann

Advances in Neural Information Processing Systems 37 (NeurIPS 2024)

Spatio-Spectral Graph Neural Networks

Simon Geisler*, Arthur Kosmala*, Daniel Herbst and Stephan Günnemann

Advances in Neural Information Processing Systems 37 (NeurIPS 2024)

Ewald-based Long-Range Message Passing for Molecular Graphs

Arthur Kosmala, Johannes Gasteiger, Nicholas Gao and Stephan Günnemann

Proceedings of the 40th International Conference on Machine Learning (ICML 2023)

Learning Integrable Dynamics with Action-Angle Networks

Ameya Daigavane, Arthur Kosmala, Miles Cranmer, Tess Smidt and Shirley Ho

Machine Learning and the Physical Sciences Workshop, NeurIPS 2023