Matthew Kowal

4

Papers

85

Total Citations

Papers (4)

Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

Understanding Video Transformers via Universal Concept Discovery

Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models