Enhancing Large Vision-Language Models for Multimodal Defect Detection via SFT-GRPO Reinforcement Learning

Authors : Hung Viet Nguyen (Inje University, Korea (South)); Hyojin Park (Gyeongnam Intelligence Innovation Center (GIIC) Kyungnam University); NamHyun Yoo (Kyungnam University Changwon); Jinhong Yang (INJE University, Korea (South))