Jinho Choi

Latest

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

ConceptScope is a scalable and automated framework for analyzing visual datasets by discovering and quantifying human-interpretable …

Sparse Autoencoders Reveal Selective Remapping of Visual Concepts During Adaptation

PatchSAE is a framework to extract interpretable concepts and their spatial attributions in vision transformers.