Avatar

Hyesu Lim

Postdoctoral Researcher

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 …
Jinho Choi, Hyesu Lim, Steffen Schneider, Jaegul Choo
PDF Code Project

CytoSAE: Interpretable Cell Embeddings for Hematology

CytoSAE is a sparse autoencoder for interpretable cell embeddings in hematology, enabling discovery of morphologically relevant …
Furkan Dasdelen, Hyesu Lim, Michele Buck, Katharina S. Götze, Carsten Marr, Steffen Schneider
PDF Code

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.
Hyesu Lim, Jinho Choi, Jaegul Choo, Steffen Schneider
PDF Code