Maximilian Dreyer
Scholar

Maximilian Dreyer

Google Scholar ID: 6Uz8sBQAAAAJ
Explainable AI Group, Fraunhofer Heinrich Hertz Institute
Explainable AI (XAI)InterpretabilityArtificial IntelligenceComputer Vision
Google Scholar↗
Citations & Impact
All-time
Citations
523
 
H-index
10
 
i10-index
10
 
Publications
18
 
Co-authors
32
list available
Contact
No contact links provided.
Publications
8 items
Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples
2026
Cited
0
From Attribution to Action: A Human-Centered Application of Activation Steering
2026
Cited
0
X-SYS: A Reference Architecture for Interactive Explanation Systems
2026
Cited
0
Towards Mechanistic Defenses Against Typographic Attacks in CLIP
2025
Cited
0
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
2025
Cited
0
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
2025
Cited
0
Mechanistic understanding and validation of large AI models with SemanticLens
2025
Cited
0
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
2022
Cited
7
Resume (English only)
Co-authors
32 total
Wojciech Samek
Wojciech Samek
Professor at TU Berlin, Head of AI Department at Fraunhofer HHI, BIFOLD Fellow
Sebastian Lapuschkin
Sebastian Lapuschkin
Head of Explainable AI, Fraunhofer Heinrich Hertz Institute
Co-author 3
Co-author 3
Thomas Wiegand
Thomas Wiegand
Professor, TU Berlin and Fraunhofer HHI, Berlin, Germany
Sebastian Bosse
Sebastian Bosse
Head of Interactive & Cognitive Systems, Fraunhofer HHI, Germany
Frederik Pahde
Frederik Pahde
Fraunhofer Heinrich Hertz Institute
Co-author 7
Co-author 7
Co-author 8
Co-author 8