作者位次 #7/8ICML 2026Poster· Deep Learning / Large Language Models
Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual Reasoning
An-Lan Wang · Guozhi Tang · Lei Liao · Hanshen Zhu · Kai Huang · Jingqun Tang · Jiaming Zhou · Kun-Yu Lin