O

Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik

Articles by Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik

Academic · 1 min

Digging Deeper: Learning Multi-Level Concept Hierarchies

arXiv:2603.10084v1 Announce Type: new Abstract: Although concept-based models promise interpretability by explaining predictions with human-understandable concepts, they typically rely on exhaustive annotations and treat concepts …

Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
8 views
Academic · 1 min

Hierarchical Concept-based Interpretable Models

arXiv:2602.23947v1 Announce Type: new Abstract: Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, …

Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik
14 views