4 papers
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
Tido Specht, Elias Benedict Krey, Nils Neukirch +1
Understanding information processing in large language models (LLMs) requires dissecting the geometric organization of their internal token representations. While existing mechanis…
Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
Nils Neukirch, Martin Maurer, Nils Strodthoff
Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification…
How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing
Elias B. Krey, Elias Krey, Nils Neukirch +1
Understanding how image-space transformations manifest in a model's internal representations is a longstanding goal in representation analysis. Prior work has shown that geometric…
FeatInv: Spatially resolved mapping from feature space to input space using conditional diffusion models
Nils Neukirch, Johanna Vielhaben, Nils Strodthoff
Internal representations are crucial for understanding deep neural networks, such as their properties and reasoning patterns, but remain difficult to interpret. While mapping from…