Stephan Wäldchen

According to our database, Stephan Wäldchen authored at least 14 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

A Family of LLMs Liberated from Static Vocabularies.

Adnen Abdessaied, Artur Baranowski, Lukas Balles, Michael Barlow, Fabien C. Y. Benureau, Felix Berkenkamp, Lukas Bluebaum, Bastian Boll, Thomas F. Burns, Björn Deiseroth, Constantin Eichenberg, David Friede, Pablo Iyu Guerrero, Ahmed Hammam, Bastian Harren, Johann Higl, Yasser Jadidi, Carina Kauf, Johannes Messner, Jan Hendrik Metzen, Max Meuer, Vedant Nanda, Pit Neitemeier, Koen Oostermeijer, Letitia Parcalabescu, Markus Pernpointner, Felix Reinfurt, Dylan Rodriquez, Grégory Schott, Philipp Siedler, Martin Simonovsky, Till Speicher, Volker Stampa, Stephan Wäldchen, Samuel Weinbach, Gregor Ziegltrum

CoRR, March, 2026

Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation.

Thomas F. Burns, Letitia Parcalabescu, Stephan Wäldchen, Michael Barlow, Gregor Ziegltrum, Volker Stampa, Bastian Harren, Björn Deiseroth

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

2025

Measuring and Guiding Monosemanticity.

Ruben Härle, Felix Friedrich, Manuel Brack, Stephan Wäldchen, Björn Deiseroth, Patrick Schramowski, Kristian Kersting

CoRR, June, 2025

2024

Interpretability Guarantees with Merlin-Arthur Classifiers.

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta

Dataset, February, 2024

Interpretability Guarantees with Merlin-Arthur Classifiers.

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Hardness of Deceptive Certificate Selection.

Stephan Wäldchen

Proceedings of the Explainable Artificial Intelligence, 2023

2022

Towards explainable artificial intelligence: interpreting neural network classifiers with probabilistic prime implicants.

Stephan Wäldchen

PhD thesis, 2022

Merlin-Arthur Classifiers: Formal Interpretability with Interactive Black Boxes.

Stephan Wäldchen, Kartikey Sharma, Max Zimmer, Sebastian Pokutta

CoRR, 2022

Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four.

Stephan Wäldchen, Sebastian Pokutta, Felix Huber

Proceedings of the International Conference on Machine Learning, 2022

A Complete Characterisation of ReLU-Invariant Distributions.

Jan MacDonald, Stephan Wäldchen

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

The Computational Complexity of Understanding Binary Classifier Decisions.

Stephan Wäldchen, Jan MacDonald, Sascha Hauch, Gitta Kutyniok

J. Artif. Intell. Res., 2021

2019

A Rate-Distortion Framework for Explaining Neural Network Decisions.

Jan MacDonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok

CoRR, 2019

The Computational Complexity of Understanding Network Decisions.

Stephan Wäldchen, Jan MacDonald, Sascha Hauch, Gitta Kutyniok

CoRR, 2019

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn.

Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller

CoRR, 2019