3 papers
cs.CV2026
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
David Restrepo, Chenwei Wu, Luis Filipe Nakayama +4
Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance rep…
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.CV2025
Multifractal Recalibration of Neural Networks for Medical Imaging Segmentation
Miguel L. Martins, Miguel T. Coimbra, Francesco Renna
Multifractal analysis has revealed regularities in many self-seeding phenomena, yet its use in modern deep learning remains limited. Existing end-to-end multifractal methods rely o…