Article

Interpretable Diffusion Models with B-cos Networks

Post-hoc Stochastic Concept Bottleneck Models

Structure is Supervision: Multiview Masked Autoencoders for Radiology

Leveraging the structure of medical data for improved representation learning

Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach

RadVLM: A multitask conversational vision-language model for radiology

Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks

scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data

Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss