activity
20242026
collaborators

9 papers

cs.AI2026

From Attribution to Action: A Human-Centered Application of Activation Steering

Tobias Labarta, Maximilian Dreyer, Katharina Weitz +2

Explainable AI (XAI) methods reveal which features influence model predictions, yet provide limited means for practitioners to act on these explanations. Activation steering of com…

cs.LG2026

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs

Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat +5

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagno…

cs.CV2026

Contrastive Semantic Projection: Faithful Neuron Labeling with Contrastive Examples

Oussama Bouanani, Jim Berend, Wojciech Samek +2

Neuron labeling assigns textual descriptions to internal units of deep networks. Existing approaches typically rely on highly activating examples, often yielding broad or misleadin…

cs.AI2026

X-SYS: A Reference Architecture for Interactive Explanation Systems

Tobias Labarta, Nhi Hoang, Maximilian Dreyer +5

The explainable AI (XAI) research community has proposed numerous technical methods, yet deploying explainability as systems remains challenging: Interactive explanation systems re…

cs.CV2026

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP

Lorenz Hufe, Constantin Venhoff, Erblina Purelku +3

Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model j…

cs.LG2025

From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance

Maximilian Dreyer, Lorenz Hufe, Jim Berend +3

Transformer-based CLIP models are widely used for text-image probing and feature extraction, making it relevant to understand the internal mechanisms behind their predictions. Whil…