Karl Henrik Johansson

Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features

Source-Guided Flow Matching

Federated Flow Matching

Are Object-Centric Representations Better At Compositional Generalization?

Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty

MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models

Bayesian Learning of Adaptive Koopman Operator with Application to Robust Motion Planning for Autonomous Trucks