CURE: Curriculum-Guided Multi-Task Training for Reliable Anatomy-Grounded Report Generation

Abstract

We propose CURE, a curriculum-guided multi-task training framework for reliable, anatomy-grounded radiology report generation. Developed with collaborators at KAUST and Pontificia Universidad Católica de Chile, CURE was selected for oral presentation at CVPR 2026.

Publication
In Proceedings of the Computer Vision and Pattern Recognition Conference
Vision-Language Models Medical Imaging Report Generation Computer Vision