activity
20242026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Foundation Model for Cardiac Time Series via Masked Latent Attention

Moritz Vandenhirtz, Samuel Ruipérez-Campillo, Simon Böhi +6

Electrocardiograms (ECGs) are among the most widely available clinical signals and play a central role in cardiovascular diagnosis. While recent foundation models (FMs) have shown…

cs.LG2026

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion

Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz +3

Machine unlearning is rapidly becoming a practical requirement, driven by privacy regulations, data errors, and the need to remove harmful or corrupted training samples. Despite th…

cs.LG2026

Post-hoc Stochastic Concept Bottleneck Models

Wiktor Jan Hoffmann, Sonia Laguna, Moritz Vandenhirtz +2

Concept Bottleneck Models (CBMs) are interpretable models that predict the target variable through high-level human-understandable concepts, allowing users to intervene on mispredi…

cs.LG2025

From Logits to Hierarchies: Hierarchical Clustering made Simple

Emanuele Palumbo, Moritz Vandenhirtz, Alain Ryser +2

The hierarchical structure inherent in many real-world datasets makes the modeling of such hierarchies a crucial objective in both unsupervised and supervised machine learning. Whi…

cs.LG2025

Interpretable Reward Modeling with Active Concept Bottlenecks

Sonia Laguna, Katarzyna Kobalczyk, Julia E. Vogt +1

We introduce Concept Bottleneck Reward Models (CB-RM), a reward modeling framework that enables interpretable preference learning through selective concept annotation. Unlike stand…

cs.LG2025

Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach

Mikael Makonnen, Moritz Vandenhirtz, Sonia Laguna +1

Concept Bottleneck Models (CBMs) aim to enhance interpretability by structuring predictions around human-understandable concepts. However, unintended information leakage, where pre…