Author name: Yanqi Wu, Xinhua Lu, Runhe Lai, Qichao Chen, Jia-Xin Zhuang, Wei-Shi Zheng, Ruixuan Wang

arXiv:2604.23729v1 Announce Type: new
Abstract: Recent studies show that using potential out-of-distribution (OOD) labels from large corpora as auxiliary information can improve OOD detection in vision-language models (VLMs). However, these methods of…