作者位次 #7/9ICML 2026Poster· Deep Learning / Large Language Models
From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models
Juncheng Wu · Hardy Chen · Haoqin Tu · Xianfeng Tang · Freda Shi · Hui Liu · Hanqing Lu · Cihang Xie · Yuyin Zhou