一作CVPR 2026Poster· Computer Vision & Pattern Recognition
Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models
Shengli Zhou · Minghang Zheng · Feng Zheng · Yang Liu
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Shengli Zhou · Minghang Zheng · Feng Zheng · Yang Liu
Shengli Zhou · Xiangchen Wang · Guanhua Chen · Feng Zheng
Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, which require spatial reasoning to identify target objects relative to anchors. Scene graphs are commonly employed to represent such relations, but reasoning over complete graphs incurs high token costs a...