Geometric Deep Learning | Reinforcement Learning | Large Language Models
PhD Student @ Autonomous Learning Robots
KIT, Karlsruhe, Germany
04/2021-now
Applied Science Intern @ TEN Search
Amazon, Luxembourg, Luxembourg
08/2024-01/2025
Journals
- Context-aware Learned Mesh-based Simulation via Trajectory-Level Meta-Learning
GDL
TMLR, 2026. P. Dahlinger, N. Freymuth, T. Hoang, T. Würth, M. Volpp, L. Kärger, G. Neumann - Learning Sub-Second Routing Optimization in Computer Networks requires Packet-Level Dynamics.
GDLRL
TMLR, 2024 A. Boltres, N. Freymuth, P. Jahnke, H. Karl, G. Neumann - Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes.
GDL
CMAME, 2024. T. Würth, N. Freymuth, C. Zimmerling, G. Neumann, L. Kärger - Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects.
ILRobotics
RA‑L, 2024. P. Scheikl, N. Schreiber, C. Haas, N. Freymuth, G. Neumann, R. Lioutikov, F. Mathis-Ullrich
Conferences
- TROLL: Trust Regions improve Reinforcement Learning for Large Language Models
LLMsRL
ICLR, 2026 (Oral). B. Becker*,N. Freymuth*, S. Thilges, F. Otto, G. Neumann - Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
GDL
ICLR, 2026. T. Hoang, A. Trenta, A. Gravina, N. Freymuth, P. Becker, D. Bacciu, G. Neumann - AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction.
GDL
NeurIPS, 2025. N. Freymuth, T. Würth, N. Schreiber, B. Gyenes, A. Boltres, J. Mitsch, A. Taranovic, T. Hoang, P. Dahlinger, P. Becker, L. Kärger, G. Neumann - MaNGO-Adaptable Graph Network Simulators via Meta-Learning.
GDL
NeurIPS, 2025. P. Dahlinger, T. Hoang, D. Blessing, N. Freymuth, G. Neumann - Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics.
GDL
NeurIPS, 2025. T. Würth, N. Freymuth, G. Neumann, L. Kärger - Swarm Reinforcement Learning for Adaptive Mesh Refinement.
GDLRL
NeurIPS, 2023. N. Freymuth, P. Dahlinger, T. Würth, S. Reisch, L. Kärger, G. Neumann - Adversarial Imitation Learning with Preferences.
IL
ICLR, 2023. A. Taranovic, A.G. Kupcsik, N. Freymuth, G. Neumann - Grounding Graph Network Simulators using Physical Sensor Observations.
GDL
ICLR, 2023. J. Linkerhägner, N. Freymuth, P.M. Scheikl, F. Mathis-Ullrich, G. Neumann - Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors.
ILRobotics
CoRL, 2022. N. Freymuth, N. Schreiber, P. Becker, A. Taranovic, G. Neumann
Under Review
- Hierarchical Multi-field Representations for Two-Stage E-commerce Retrieval
LLMsRetrieval
N. Freymuth, D. Liu, T. Ricatte, S. Manseur - Adaptive Swarm Mesh Refinement using Deep Reinforcement Learning with Local Rewards
GDLRL
N. Freymuth, P. Dahlinger, T. Würth, S. Reisch, L. Kärger, G. Neumann
Workshops
- KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty.
RL
“Next Generation of Sequence Modeling Architectures” and “Aligning Reinforcement Learning Experimentalists and Theorists” @ICML, 2024. P. Becker, N. Freymuth, G. Neumann - Iterative Sizing Field Prediction for Adaptive Mesh Generation From Expert Demonstrations.
GDL
“AI4Science” @ICML, 2024. N. Freymuth, P. Dahlinger, T. Würth, P. Becker, A. Taranovic, O. Grönheim, L. Kärger, G. Neumann - Latent Task-Specific Graph Network Simulators.
GDL
“AI4Science” @NeurIPS, 2023. P. Dahlinger, N. Freymuth, M. Volpp, T. Hoang, G. Neumann - Swarm Reinforcement Learning for Adaptive Mesh Refinement (v1).
GDLRL
“Physics for Machine Learning” @ICLR, 2023. N. Freymuth, P. Dahlinger, T. Würth, L. Kärger, G. Neumann - Bimodal speech emotion recognition using pre-trained language models.
LLMs
“Life-Long Learning for Spoken Language Systems” @ASRU, 2019. V. Heusser*, N. Freymuth*, S. Constantin, A. Waibel
Theses Supervision and Teaching
Bachelor’s Theses (Selection)
- Autonomous Partitioning of Heterogeneous Swarm Systems
- Swarm Reinforcement Learning with Graph Neural Networks
Teaching
- Teaching Assistant for the “Reinforcement Learning” Lecture @ KIT
- Seminar and Praktikum “Robot Learning” @ KIT
Misc. Projects
- Efficient Swarm Reinforcement Learning from Human Feedback
- Spatial Credit Assignment for Swarm Reinforcement Learning
Master’s Theses (Selection)
- Rotation-Equivariant Graph Neural Networks for mesh-based simulations
- Adaptive Mesh HP-Refinement with Swarm Reinforcement Learning
- Graph Diffusion for Adaptive Mesh R-Refinement
- Adaptive Mesh Refinement from Human Feedback
- Variational Swarm Reinforcement Learning for Predictive Models of Deformable Objects
- Swarm Reinforcement Learning in Limited Visibility with Graph Neural Networks
- Physical Simulation from Observation using Graph Neural Networks