Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning Yihong Tang,Ao Qu, Zhaokai Wang,Dingyi Zhuang, Zhaofeng Wu,Wei Ma,Shenhao Wang,Yunhan Zheng,Zhan Zhao,Jinhua Zhaoarxiv(2024)引用 0|浏览8暂无评分AI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要