Introducing CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
Microsoft 2 months ago 41
CARE-X, a chest X-ray vision-language model, was introduced with auxiliary supervision and DAPO reinforcement learning to support calibrated classification, location grounding, and report generation in one system. It reached 94% overall accuracy on the ReXVQA benchmark (41,007 question–answer pairs) as of August 2026. The work changes radiology VLMs by combining structured, tunable confidence outputs and tool-augmented quantitative measurement with generative reporting rather than relying only on free-text predictions.
