Yuxuan Luo

Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

DPO-Clin is proposed, a novel post-training framework that focuses preference optimization on clinical findings and cross-modal alignment and achieves superior performance over existing DPO-based MRG methods, exhibiting robust generalizability across distinct baseline architectures and diverse medical imaging modalitie...