8b parameter model (EVLF-FM) surpasses clinicians in multimodal understanding
paper released two days ago: "A clinical multimodal vision language foundation model with fine-grain explainability" published in NATURE. https://www.nature.com/articles/s41591-026-04655-5 this shit is INSANE! 8b parameters and surpassing clinicians in topics like radiology, dermatology etc.