Wojciech Samek
Scholar

Wojciech Samek

Google Scholar ID: 7aQwO08AAAAJ
Professor at TU Berlin, Head of AI Department at Fraunhofer HHI, BIFOLD Fellow
Deep LearningInterpretabilityExplainable AITrustworthy AIFederated Learning
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
42,166
 
H-index
69
 
i10-index
164
 
Publications
20
 
Co-authors
18
list available
Contact
No contact links provided.
Publications
46 items
Predicting Future Behaviors in Reasoning Models Enables Better Steering
2026
Cited
0
Fast & Faithful Function Vectors
2026
Cited
0
The Case for Model Science: Verify, Explore, Steer, Refine
2026
Cited
0
$\alpha$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
2026
Cited
0
Judge Circuits
2026
Cited
0
Playing the network backward: A Game Theoretic Attribution Framework
2026
Cited
0
Knowledge-Free Correlated Agreement for Incentivizing Federated Learning
2026
Cited
0
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
2026
Cited
0
Resume (English only)
Co-authors
18 total
Klaus-Robert Müller
Klaus-Robert Müller
TU Berlin & Korea University & Google DeepMind & Max Planck Institute for Informatics, Germany
Sebastian Lapuschkin
Sebastian Lapuschkin
Head of Explainable AI, Fraunhofer Heinrich Hertz Institute
Grégoire Montavon
Grégoire Montavon
Professor, Charité / BIFOLD
Alexander Binder
Alexander Binder
Professor, ScaDS.AI and Faculty of Math and Computer Science, Uni Leipzig, Germany
Thomas Wiegand
Thomas Wiegand
Professor, TU Berlin and Fraunhofer HHI, Berlin, Germany
Sebastian Bosse
Sebastian Bosse
Head of Interactive & Cognitive Systems, Fraunhofer HHI, Germany
Motoaki Kawanabe
Motoaki Kawanabe
Senior Researcher, Advanced Telecommunications Research Institute International
Nils Strodthoff
Nils Strodthoff
Professor for eHealth/AI4Health, Oldenburg University, Germany