collaborators

7 papers

physics.flu-dyn2026

Modern aerodynamics models do not capture important unsteady forces--the failure of the quasi-steady approximation

Victoria M. Malarczyk, Marcus Hultmark

Aerodynamic unsteadiness is inherent to the operation of many engineering applications, especially those that involve large-scale rotating blades, such as modern wind turbines. Ove…

stat.ME2026

Deep Shape Regression for Planar Curves with Multimodal Covariates

Manuel Pfeuffer, Roshan Prakash Rane, Hadya Yassin +2

The shape of a planar curve is the geometric information that remains once translation, rotation, scale and reparametrisation are removed and is of interest in many health applicat…

cs.LG2026

Measurement noise limits the advantage of nonlinear models over linear models in biomedical prediction

Marc-Andre Schulz, Kerstin Ritter

On biomedical tabular data, flexible models such as deep networks, gradient-boosted trees, and kernel methods are repeatedly matched or beaten by linear and logistic regression giv…

cs.LG2026

Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics

Sam Gijsen, Michał Łukomski, Marc-André Schulz +1

Flow matching and diffusion models enable conditional generation across domains ranging from images to proteins, with recent extensions to out-of-distribution contexts. Yet generat…

cs.CL2026

Beyond Binary: Speech Representations Across the Cognitive Score Hierarchy

Serli Kopar, Roshan Prakash Rane, Christian Mychajliw +6

This study examines the relationship between speech representations and the hierarchical structure of cognitive assessment in mild cognitive impairment. Utilizing 5,754 German neur…

cs.LG2026

Brain-Semantoks: Learning Semantic Tokens of Brain Dynamics with a Self-Distilled Foundation Model

Sam Gijsen, Marc-Andre Schulz, Kerstin Ritter

The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cogniti…