arXivYifan Cao, Xiaocui Yang, Faxian Wan, Shi Feng, Daling Wang, Yifei ZhangTue, Jun 2, 2026, 5:30 AM PDT

score 17.1

Model learns to segment objects from complex descriptions

Original: \textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation

Writing ELI5 summary…