University of Stuttgart · MLS Lab

Machine learning and
simulation lab

We are a research group at the University of Stuttgart. We develop and analyze new machine learning methods, with applications in the natural sciences and engineering.

MLS group members outdoors with mountains in the background.

Machine Learning and Simulation LabStuttgart, Germany

Affiliations

Internationally recognized for engineering and computer science

Stuttgart Center for Simulation Science

European Laboratory for Learning and Intelligent Systems

International Max Planck Research School for Intelligent Systems

01 / Research

Research areas

Our work focuses on geometric and structure-aware learning, generative and probabilistic models, and machine learning for science and engineering.

Geometric and
structure-aware learning

We design graph neural networks and equivariant representations that incorporate geometric and relational structure, and analyze their properties.

Graph neural networks
Equivariance

Research topic

Generative &
probabilistic models

We develop generative models and inference methods that incorporate structure and constraints, aiming for efficient sampling and controllable generation.

Diffusion models
Controllable generation

Research topic

Machine learning for
science and engineering

We develop new physics-aware models and neural solvers for scientific simulation, with applications in computational chemistry and fluid dynamics.

Neural PDE solvers
Molecular learning

Research topic

02 / Publications

Selected publications

All publications

NeurIPS 2026Generative modeling

SymDrift: One-Shot Generative Modeling under Symmetries

Samir Darouich, Vinh Tong, Lluís Pastor-Pérez, Tanja Bien, Loay Mualem, Mathias Niepert

ICML 2026Scientific simulation

SMART: Scalable Mesh-free Aerodynamic Simulations from Raw Geometries using a Transformer-based Surrogate Model

Jan Hagnberger, Mathias Niepert

NeurIPS 2025Oral presentation

Learning (Approximately) Equivariant Networks via Constrained Optimization

Andrei Manolache, Luiz Chamon, Mathias Niepert

NeurIPS 2025Spotlight presentation

CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs

Jan Hagnberger, Daniel Musekamp, Mathias Niepert

See the publication archive for bibliographic details and available paper links.

03 / People

Group members

All group members

Group leader

Mathias Niepert

Professor · University of Stuttgart

Prof. Mathias Niepert leads the MLS Lab at the Institute for Artificial Intelligence. His research focuses on machine learning methods that incorporate physical and geometric structure.

He is an ELLIS member, a faculty member of IMPRS-IS, and Chief Scientific Advisor at NEC Laboratories Europe.

Profile Email LinkedIn