AIConfPaper
← Search

Niklas Freymuth

12 accepted papers

2026

Fourier Features Let Agents Learn High Precision Policies with Imitation Learning

Balázs Gyenes, Emiliyan Gospodinov, Jan Frieling, Enrico Krohmer, Nicolas Schreiber, Xiaogang Jia +2
ICML 2026poster

Various 3D modalities have been proposed for high-precision imitation learning tasks to compensate for the short-comings of RGB-only policies. Modalities that explicitly represent positions in Cartesian space, such as most point cloud encoder architectures, have an inherent advantage over purely ima…

Cited by 0Source ↗code ↗Scholar ↗
2026

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Tai Hoang, Alessandro Trenta, Alessio Gravina, Niklas Freymuth, Philipp Becker, Davide Bacciu +1
ICLR 2026poster

Learning to simulate complex physical systems from data has emerged as a promising way to overcome the limitations of traditional numerical solvers, which often require prohibitive computational costs for high-fidelity solutions. Recent Graph Neural Simulators (GNSs) accelerate simulations by learni…

Cited by 0Source ↗code ↗Scholar ↗
2026

PAWS: Preference Learning with Advantage-Weighted Segments

Aleksandar Taranovic, Onur Celik, Niklas Freymuth, Ge Li, Serge Thilges, Huy Le +3
ICML 2026poster

Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates…

Cited by 0Source ↗Scholar ↗
2026

TROLL: Trust Regions Improve Reinforcement Learning for Large Language Models

Philipp Becker, Niklas Freymuth, Serge Thilges, Fabian Otto, Gerhard Neumann
ICLR 2026oral

Reinforcement Learning (RL) with PPO-like clip objectives has become the standard choice for reward-based fine-tuning of large language models (LLMs). Although recent work has explored improved estimators of advantages and normalization, the clipping mechanism itself has remained untouched. Origina…

Cited by 0Source ↗code ↗Scholar ↗
2025

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth, Tobias Würth, Nicolas Schreiber, Balázs Gyenes, Andreas Boltres, Johannes Mitsch +6
NeurIPS 2025poster

The cost and accuracy of simulating complex physical systems using the Finite Element Method (FEM) scales with the resolution of the underlying mesh. Adaptive meshes improve computational efficiency by refining resolution in critical regions, but typically require task-specific heuristics or cumbers…

Cited by 0Source ↗code ↗Scholar ↗
2025

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Tobias Würth, Niklas Freymuth, Gerhard Neumann, Luise Kärger
NeurIPS 2025spotlight

Graph-based learned simulators have emerged as a promising approach for simulating physical systems on unstructured meshes, offering speed and generalization across diverse geometries. However, they often struggle with capturing global phenomena, such as bending or long-range correlations usually oc…

Cited by 0Source ↗Scholar ↗
2025

MaNGO — Adaptable Graph Network Simulators via Meta-Learning

Philipp Dahlinger, Tai Hoang, Denis Blessing, Niklas Freymuth, Gerhard Neumann
NeurIPS 2025poster

Accurately simulating physics is crucial across scientific domains, with applications spanning from robotics to materials science. While traditional mesh-based simulations are precise, they are often computationally expensive and require knowledge of physical parameters, such as material properties.…

Cited by 0Source ↗Scholar ↗
2024

Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects

Paul Maria Scheikl, Nicolas Schreiber, Christoph Haas, Niklas Freymuth, Gerhard Neumann, Rudolf Lioutikov +1
RA-L 2024

Policy learning in robot-assisted surgery (RAS) lacks data efficient and versatile methods that exhibit the desired motion quality for delicate surgical interventions. To this end, we introduce Movement Primitive Diffusion (MPD), a novel method for imitation learning (IL) in RAS that focuses on gent

Cited by 76Source ↗code ↗Scholar ↗
2023

Adversarial Imitation Learning with Preferences

Aleksandar Taranovic, Andras Gabor Kupcsik, Niklas Freymuth, Gerhard Neumann
ICLR 2023poster

Designing an accurate and explainable reward function for many Reinforcement Learning tasks is a cumbersome and tedious process. Instead, learning policies directly from the feedback of human teachers naturally integrates human domain knowledge into the policy optimization process. However, differ…

Cited by 13Source ↗PDF ↗Scholar ↗
2023

Grounding Graph Network Simulators using Physical Sensor Observations

Jonas Linkerhägner, Niklas Freymuth, Paul Maria Scheikl, Franziska Mathis-Ullrich, Gerhard Neumann
ICLR 2023poster

Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned Graph Network Simulators produced accurate mesh-based simulations while requiring only a fraction of the computational…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2023

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Niklas Freymuth, Philipp Dahlinger, Tobias Daniel Würth, Simon Reisch, Luise Kärger, Gerhard Neumann
NeurIPS 2023poster

The Finite Element Method, an important technique in engineering, is aided by Adaptive Mesh Refinement (AMR), which dynamically refines mesh regions to allow for a favorable trade-off between computational speed and simulation accuracy. Classical methods for AMR depend on task-specific heuristics or…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2022

Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors

Niklas Freymuth, Nicolas Schreiber, Aleksandar Taranovic, Philipp Becker, Gerhard Neumann
CoRL 2022poster

Humans intuitively solve tasks in versatile ways, varying their behavior in terms of trajectory-based planning and for individual steps. Thus, they can easily generalize and adapt to new and changing environments. Current Imitation Learning algorithms often only consider unimodal expert demonstratio…

Cited by 5Source ↗code ↗Scholar ↗