Representation and Dynamics Learning for Robotics

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

Tai Hoang, Alessandro Trenta, Alessio Gravina, Niklas Freymuth, Philipp Becker, Davide Bacciu, Gerhard Neumann
Published in International Conference on Learning Representations (ICLR), 2026

Paper

Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects

Tai Hoang, Huy Le, Philipp Becker, Vien Anh Ngo, Gerhard Neumann
Published in International Conference on Learning Representations (ICLR), 2025

Paper

Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker, Stefan Geyer, Gerhard Neumann
Published in Workshop on Adaptive Foundation Models @ NeurIPS, 2024

Paper

PointPatchRL-Masked Reconstruction Improves Reinforcement Learning on Point Clouds

Balazs Gyenes, Nikolai Franke, Philipp Becker, Gerhard Neumann
Published in Conference on Robot Learning (CoRL), 2024

Paper | Code | Project Page

MuTT: A Multimodal Trajectory Transformer for Robot Skills

Claudius Kienle, Benjamin Alt, Onur Celik, Philipp Becker, Darko Katic, Rainer Jakel, Gerhard Neumann
Published in International Conference on Intelligent Robots and Systems (IROS), 2024

Paper

KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertainty

Philipp Becker, Niklas Freymuth, Gerhard Neumann
Published in Aligning Reinforcement Learning Experimentalists and Theorists Workshop @ ICML; Next Generation of Sequence Modeling Architectures Workshop @ ICML; Training Agents with Foundation Models @ RLC, 2024

Paper

Combining Reconstruction and Contrastive Methods for Multimodal Representations in RL

Philipp Becker, Sebastian Mossburger, Fabian Otto, Gerhard Neumann
Published in Reinforcment Learning Conference (RLC), 2024

Paper | Code | Project Page

On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning

Philipp Becker, Gerhard Neumann
Published in Transactions on Machine Learning Research (TMLR), 2022

Paper | Code

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Vaisakh Shaj Kumar, D Büchler, R Sonker, Philipp Becker, Gerhard Neumann
Published in International Conference on Learning Representations (ICLR), 2022

Paper | Code

End-to-End Learning of Hybrid Inverse Dynamics Models for Precise and Compliant Impedance Control

Moritz Reuss, Niels van Duijkeren, Robert Krug, Philipp Becker, Vaisakh Shaj, Gerhard Neumann
Published in Robotics: Science and Systems (RSS), 2022

Paper

Switching Recurrent Kalman Networks

Giao Nguyen-Quynh, Philipp Becker, Chen Qiu, Maja Rudolph, Gerhard Neumann
Published in Machine Learning for Autonomous Driving Workshop @ NeurIPS, 2021

Paper

Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learning

Vaisakh Shaj, Philipp Becker, Dieter Büchler, Harit Pandya, Niels van Duijkeren, C James Taylor, Marc Hanheide, Gerhard Neumann
Published in Conference on Robot Learning (CoRL), 2020

Paper | Code

Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces

Philipp Becker, Harit Pandya, Gregor Gebhardt, Cheng Zhao, James Taylor, Gerhard Neumann
Published in International Conference on Machine Learning (ICML), 2019

Paper | Code