Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings
David Restrepo, Miguel L Martins, Chenwei Wu +5
Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contri…
cs.LG2025
Representation Learning of Lab Values via Masked AutoEncoders
David Restrepo, Chenwei Wu, Yueran Jia +5
Accurate imputation of missing laboratory values in electronic health records (EHRs) is critical to enable robust clinical predictions and reduce biases in AI systems in healthcare…
cs.LG2024
Multimodal Deep Learning for Low-Resource Settings: A Vector Embedding Alignment Approach for Healthcare Applications
David Restrepo, Chenwei Wu, Sebastián Andrés Cajas +3
Large-scale multi-modal deep learning models have revolutionized domains such as healthcare, highlighting the importance of computational power. However, in resource-constrained re…