Similar Items: Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
- Crafting Reversible SFT Behaviors in Large Language Models
- Do Sparse Autoencoders Capture Concept Manifolds?
- Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
- Physiologically Grounded Driver Behavior Classification: SHAP-Driven Elite Feature Selection and Hybrid Gradient Boosting for Multimodal Physiological Signals
- Spectral Model eXplainer: a chemically-grounded explainability framework for spectral-based machine learning models