Author

Thomas Trappenberg

h-index 7 View on Semantic Scholar

We have 2 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Jul 2026

Uncertainty quantification for trustworthy deep learning: Methods and measures

This survey provides a structured, critical review of methods for Uncertainty Quantification in deep learning, scoped to ensemble-based and approximate Bayesian approaches and the measures used to summarize their outputs.

H. M. Gillis, Thomas Trappenberg · arXiv.org · 0 citations

Jul 2026

Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification

Viewing OC as a last-layer ensemble also organizes detectors into a two-axis taxonomy and exposes the OC score as a magnitude, motivating a scale-invariant, label-free direction score that repairs its near-OOD failure.

H. M. Gillis, Isaac Xu, Gabriel Spadon et al. · arXiv.org · 0 citations