作者位次 #3/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks
Qihua Dong · Kuo Yang · Lin Ju · Handong Zhao · Yitian Zhang · Yizhou Wang · Huimin Zeng · Jianglin Lu · Yun Fu