微软研究院推出 CARE-X:面向临床可用的放射学 VLM
微软研究院发布研究模型 CARE-X,基于 SigLIP2-so400M 视觉编码器和 Phi-4-mini-instruct(3.8B)语言模型,通过辅助监督、DAPO 强化学习与工具增强测量统一生成与判别能力。在 ReXVQA 基准(41,007 组问答)上达到 94% 总体准确率,比次优公开模型高 6 个百分点,并于 2026 年 8 月位列 ReXrank RexVQA 榜首。该模型为研究用途,尚未获监管批准,不用于临床诊断。
Research Note: CARE-X is a research model and not a Microsoft product offering or medical device. It has not been cleared or approved by any regulatory authority and is not intended for clinical diagnosis, screening, or patient care. The results described below are retrospective research findings and do not establish the safety, effectiveness, or suitability of CARE-X for any clinical use. References to potential workflows describe areas for future research, not currently available capabilities
匹配字段正文

