Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Microsoft Research released CARE-X, a unified chest X-ray vision-language research model for report generation and structured prediction. It rewards clinical correctness using multitask reinforcement learning (DAPO). Generation and dual-inference modes cover lesion presence and negation, localisation, multilabel classification, catheter and tube malposition detection, and localisation of 29 anatomical regions.
Selection record
Not admittedSum of both 80 < twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：介绍放射学视觉语言模型CARE-X及训练评测
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Microsoft Research · microsoft.com