Publications

Project-Specific Publications and Preprints

The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
J. Herbst, J. H. Lee, and S. Wermter
International Conference on Machine Learning (ICML), to appear, 2026
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
G. Schwalbe, M. Keser, M. Bayerkuhnlein, E. Heinert, A. Mütze, M. Keller, S. Tiwari, G. Mikriukov, D. Wolter, J. H. Lee, and M. Rottmann
International Joint Conference on Artificial Intelligence (IJCAI), to appear, 2026
Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities
H. H. Lehmann, J. H. Lee, S. Schockaert, and S. Wermter
Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026
Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
J. H. Lee, A. Lauscher, and S. V. Albrecht
Presented at LLM-based Multi-Agent Systems: Towards Responsible, Reliable, and Scalable Agentic Systems (LaMAS), 2026

Related Preparatory Work

Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
J. H. Lee, G. Mikriukov, G. Schwalbe, S. Wermter, and D. Wolter
European Conference on Computer Vision (ECCV) Workshops, 2024
From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks
J. H. Lee, S. Lanza, and S. Wermter
Neurosymbolic Artificial Intelligence (NAI), 2024
Read Between the Layers: Leveraging Multi-Layer Representations for Rehearsal-Free Continual Learning with Pre-Trained Models
K. Ahrens, H. H. Lehmann, J. H. Lee, and S. Wermter
Transactions on Machine Learning Research (TMLR), 2024
Visually Grounded Continual Language Learning with Selective Specialization
K. Ahrens, L. Bengtson, J. H. Lee, and S. Wermter
Findings of the Association for Computational Linguistics: Empirical Methods in Natural Language Processing (EMNLP Findings), 2023
Neuro-Symbolic Spatio-Temporal Reasoning
J. H. Lee, M. Sioutis, K. Ahrens, M. Alirezaie, M. Kerzel, and S. Wermter
Compendium of Neurosymbolic Artificial Intelligence, 2023
Learning Bidirectional Action-Language Translation with Limited Supervision and Testing with Incongruent Input
O. Ozdemir, M. Kerzel, C. Weber, J. H. Lee, M. B. Hafez, P. Bruns, and S. Wermter
Applied Artificial Intelligence, 2023
What Is Right for Me Is Not yet Right for You: A Dataset for Grounding Relative Directions Via Multi-Task Learning
J. H. Lee, M. Kerzel, K. Ahrens, C. Weber, and S. Wermter
International Joint Conference on Artificial Intelligence (IJCAI), 2022
Language Model-Based Paired Variational Autoencoders for Robotic Language Learning
O. Ozdemir, M. Kerzel, C. Weber, J. H. Lee, and S. Wermter
IEEE Transactions on Cognitive and Developmental Systems (TCDS), 2022
Robotic Occlusion Reasoning for Efficient Object Existence Prediction
M. Li, C. Weber, M. Kerzel, J. H. Lee, Z. Zeng, Z. Liu, and S. Wermter
International Conference on Intelligent Robots and Systems (IROS), 2021
Generalization in Multimodal Language Learning from Simulation
A. Eisermann, J. H. Lee, C. Weber, and S. Wermter
International Joint Conference on Neural Networks (IJCNN), 2021