一作ACL 2026Poster· Natural Language Processing
Diagnosing Spatial Consistency across Perspectives and Viewpoints in Large Vision-Language Models
Yoonji Kim · Jieun Kim · Yujin Jeong · Sung-Bae Cho
摘要
Consistent reasoning about 3D spatial relations across changing viewpoints is fundamental for Embodied AI agents operating in dynamic environments. While Large Vision-Language Models (LVLMs) have advanced multimodal perception, their ability to maintain spatial consistency across diverse perspect...