A clinical multimodal vision language foundation model with fine-grain explainability.
EVLF-FM is introduced, a multimodal vision language foundation model that combines broad diagnostic capabilities with fine-grained explainability and a hybrid training strategy combining supervised and visual reinforcement fine-tuning enables EVLF-FM to generate clinically interpretable explanations aligned with visual...
Yang Bai, Hao-Ran Cheng, Yang Zhou et al.
· Nature Medicine · 0 citations