Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Spectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based Inference
Xin Zhao, Nico Scherf, Robert Trampel +2
Simulation-based inference (SBI) has become a powerful approach to Bayesian inference in complex scientific models whose likelihoods are difficult or impossible to evaluate. Amorti…
cs.AI2026
From Clever Hans to Scientific Discovery: Interpreting EEG Foundational Transformers with LRP
Justus Meyer zu Bexten, Nico Scherf, Bogdan Franczyk +1
Emerging foundation models (FMs) in electroencephalography (EEG) promise a path to scale deep learning in diagnostics and brain-computer interfaces despite data scarcity, yet their…
cs.LG2026
Relative Geometry of Neural Forecasters: Linking Accuracy and Alignment in Learned Latent Geometry
Deniz Kucukahmetler, Maximilian Jean Hemmann, Julian Mosig von Aehrenfeld +4
Neural networks can accurately forecast complex dynamical systems, yet how they internally represent underlying latent geometry remains poorly understood. We study neural forecaste…