3 papers
cs.AI2025
LayerCake: Token-Aware Contrastive Decoding within Large Language Model Layers
Jingze Zhu, Yongliang Wu, Wenbo Zhu +7
Large language models (LLMs) excel at natural language understanding and generation but remain vulnerable to factual errors, limiting their reliability in knowledge-intensive tasks…
cs.CV2025
Disentangling Polysemantic Channels in Convolutional Neural Networks
Robin Hesse, Jonas Fischer, Simone Schaub-Meyer +1
Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mec…
cs.CV2025
Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
Nhi Pham, Artur Jesslen, Bernt Schiele +2
With the rise of deep neural networks, especially in safety-critical applications, robustness and interpretability are crucial to ensure their trustworthiness. Recent advances in 3…