Publication | Closed Access

A Foundation Language-Image Model of the Retina (FLAIR): encoding expert knowledge in text supervision

Natural Language ProcessingMultimodal LlmKnowledge RepresentationExpert KnowledgeEngineeringText-to-image RetrievalFoundation Language-image ModelText SupervisionVisual ReasoningVisual GroundingComputational LinguisticsEye TrackingVision Language ModelLanguage StudiesLinguistics