3 papers
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.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…
cs.AI2024
DF-DM: A foundational process model for multimodal data fusion in the artificial intelligence era
David Restrepo, Chenwei Wu, Constanza Vásquez-Venegas +3
In the big data era, integrating diverse data modalities poses significant challenges, particularly in complex fields like healthcare. This paper introduces a new process model for…