Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
BeginnerJiaqi Tang, Jianmin Chen et al.Dec 19arXiv
Robust-R1 teaches vision-language models to notice how a picture is damaged, think through what that damage hides, and then answer as if the picture were clear.
#Robust-R1#degradation-aware reasoning#multimodal large language models