collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Unsupervised Symbolic Anomaly Detection

Md Maruf Hossain, Tim Katzke, Simon Klüttermann +1

We propose SYRAN, an unsupervised anomaly detection method based on symbolic regression. Instead of encoding normal patterns in an opaque, high-dimensional model, our method learns…

cs.LG2026

FoMo X: Modular Explainability Signals for Outlier Detection Foundation Models

Simon Klüttermann, Tim Katzke, Phuong Huong Nguyen +1

Tabular foundation models, specifically Prior-Data Fitted Networks (PFNs), have revolutionized outlier detection (OD) by enabling unsupervised zero-shot adaptation to new datasets…

cs.LG2025

On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification

Faried Abu Zaid, Tim Katzke, Emmanuel Müller +1

Unsupervised anomaly detection is often framed around two widely studied paradigms. Deep one-class classification, exemplified by Deep SVDD, learns compact latent representations o…

cs.LG2025

Unsupervised Surrogate Anomaly Detection

Simon Klüttermann, Tim Katzke, Emmanuel Müller

In this paper, we study unsupervised anomaly detection algorithms that learn a neural network representation, i.e. regular patterns of normal data, which anomalies are deviating fr…

cs.LG2025

A Cautionary Tale About "Neutrally" Informative AI Tools Ahead of the 2025 Federal Elections in Germany

Ina Dormuth, Sven Franke, Marlies Hafer +6

In this study, we examine the reliability of AI-based Voting Advice Applications (VAAs) and large language models (LLMs) in providing objective political information. Our analysis…