collaborators

12 papers

cs.LG2026

Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data

Dan DeGenaro, Xin Li, Obed Amo +4

We introduce FLASH-MAX, a shallow, exact-by-construction neural network architecture for predicting homogeneous electromagnetic fields from sparse pointwise observations. Each hidd…

cs.IR2026

ECLASS-Augmented Semantic Product Search for Electronic Components

Nico Baumgart, Markus Lange-Hegermann, Jan Henze

Efficient semantic access to industrial product data is a key enabler for factory automation and emerging LLM-based agent workflows, where both human engineers and autonomous agent…

cs.LG2026

Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme

Ruwen Fulek, Markus Lange-Hegermann

We present a simple yet effective generative model for time series, based on a Recurrent Variational Autoencoder that we refer to as AEQ-RVAE-ST. Recurrent layers often struggle wi…

cs.CV2025

Investigation of the Impact of Synthetic Training Data in the Industrial Application of Terminal Strip Object Detection

Nico Baumgart, Markus Lange-Hegermann, Mike Mücke

In industrial manufacturing, deploying deep learning models for visual inspection is mostly hindered by the high and often intractable cost of collecting and annotating large-scale…

math.OC2025

Physics-informed Gaussian Processes as Linear Model Predictive Controller with Constraint Satisfaction

Jörn Tebbe, Andreas Besginow, Markus Lange-Hegermann

Model Predictive Control evolved as the state of the art paradigm for safety critical control tasks. Control-as-Inference approaches thereof model the constrained optimization prob…

cs.LG2025

Comparing EPGP Surrogates and Finite Elements Under Degree-of-Freedom Parity

Obed Amo, Samit Ghosh, Markus Lange-Hegermann +2

We present a new benchmarking study comparing a boundary-constrained Ehrenpreis--Palamodov Gaussian Process (B-EPGP) surrogate with a classical finite element method combined with…