activity
20222026
most citedRevealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations

3 citations · 3 across the 5 of their papers we have counts for

collaborators

10 papers

cs.CV2026

Concept-based explanation of gene expression prediction from H&E images

Amos Muench, Jonathan Thielmann, Reduan Achtibat +9

Recent advances in pathology foundation models have enabled accurate prediction of spatial transcriptomics (ST) from routine H&E images. However, existing explainability methods fo…

cs.CL2026

Fast & Faithful Function Vectors

Minh An Pham, Anton Segeler, Thomas Wiegand +4

Function vectors (FVs) are task representations elicited during in-context learning that can be used to steer Large Language Models (LLMs). However, design choices in their formula…

cs.LG2025

Attribution-Guided Decoding

Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat +3

The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard dec…

cs.LG2025

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.CL2025

The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation

Patrick Kahardipraja, Reduan Achtibat, Thomas Wiegand +2

Large language models are able to exploit in-context learning to access external knowledge beyond their training data through retrieval-augmentation. While promising, its inner wor…

cs.AI2024

Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers

Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat +3

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational r…