Stephan Wäldchen

17 papers A* 1A 2Journal 11Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Family of LLMs Liberated from Static Vocabularies.
CoRR
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
2026 — conf
Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation.
EACL (Volume 1: Long Papers)
Thomas F. Burns, Letitia Parcalabescu, Stephan Wäldchen, Michael Barlow, Gregor Ziegltrum, Volker Stampa, Bastian Harren, Björn Deiseroth
2025 J jnl
Aleph-Alpha-GermanWeb: Improving German-language LLM pre-training with model-based data curation and synthetic data generation.
CoRR
Thomas F. Burns, Letitia Parcalabescu, Stephan Wäldchen, Michael Barlow, Gregor Ziegltrum, Volker Stampa, Bastian Harren, Björn Deiseroth
2025 J jnl
Measuring and Guiding Monosemanticity.
CoRR
Ruben Härle, Felix Friedrich, Manuel Brack, Stephan Wäldchen, Björn Deiseroth, Patrick Schramowski, Kristian Kersting
2024 A conf
Interpretability Guarantees with Merlin-Arthur Classifiers.
AISTATS
Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, Sebastian Pokutta
2023 — conf
Hardness of Deceptive Certificate Selection.
xAI (3)
Stephan Wäldchen
2023 J jnl
Hardness of Deceptive Certificate Selection.
CoRR
Stephan Wäldchen
2022 A conf
A Complete Characterisation of ReLU-Invariant Distributions.
AISTATS
Jan MacDonald, Stephan Wäldchen
2022 J jnl
Merlin-Arthur Classifiers: Formal Interpretability with Interactive Black Boxes.
CoRR
Stephan Wäldchen, Kartikey Sharma, Max Zimmer, Sebastian Pokutta
2022 — —
Towards explainable artificial intelligence: interpreting neural network classifiers with probabilistic prime implicants.
Stephan Wäldchen
2022 A* conf
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four.
ICML
Stephan Wäldchen, Sebastian Pokutta, Felix Huber
2022 J jnl
Training Characteristic Functions with Reinforcement Learning: XAI-methods play Connect Four.
CoRR
Stephan Wäldchen, Felix Huber, Sebastian Pokutta
2021 J jnl
A Complete Characterisation of ReLU-Invariant Distributions.
CoRR
Jan MacDonald, Stephan Wäldchen
2021 J jnl
The Computational Complexity of Understanding Binary Classifier Decisions.
J. Artif. Intell. Res.
Stephan Wäldchen, Jan MacDonald, Sascha Hauch, Gitta Kutyniok
2019 J jnl
A Rate-Distortion Framework for Explaining Neural Network Decisions.
CoRR
Jan MacDonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok
2019 J jnl
The Computational Complexity of Understanding Network Decisions.
CoRR
Stephan Wäldchen, Jan MacDonald, Sascha Hauch, Gitta Kutyniok
2019 J jnl
Unmasking Clever Hans Predictors and Assessing What Machines Really Learn.
CoRR
Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller