The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
International Conference on Machine Learning 2026
I am a principal investigator at the University of Hamburg, where I co-lead the DFG projects LUMO and E4-MALM. My research focuses on trustworthy AI systems that can reason robustly and explain their behavior.
Research Interests
Latest News
- Aug 2026 5th International Workshop on Spatio-Temporal Reasoning and Learning (STRL 2026), held at IJCAI-ECAI 2026 in Bremen (LinkedIn post).
- Aug 2026 Bias Leaves a Gradient Trail: Label-Free Bias Identification via Gradient Probes on Concept Decompositions has received the Springer Best Paper Award 🏆 at KI 2026.
- Aug 2026 Tutorial on Explaining Vision and Language Models — A Concept-Based Approach at KI 2026.
Recent Publications
Explaining, Verifying and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
International Joint Conference on Artificial Intelligence 2026
Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities
European Chapter of the Association for Computational Linguistics 2026
Recent Teaching
- Neural Networks Course
- Seminar Understanding Large Language Models Seminar
- Explaining Vision and Language Models: A Concept-Based Approach Tutorial
Recent Blog Posts
Deep Learning Courses and Books for Beginners
A curated list of deep learning resources for CS students who want to understand recent research papers.
Common LaTeX Mistakes by Newbies
A list of common LaTeX mistakes that beginners often make, with examples of correct usage.