作者位次 #2/10ACL 2026Poster· Natural Language Processing
C ity C ube: Benchmarking Cross-view Spatial Reasoning on Vision-Language Models in Urban Environments
Haotian Xu · Yue Hu · Zhengqiu Zhu · Chen Gao · Ziyou Wang · Junreng Rao · Wenhao Lu · Weishi Li · Quanjun Yin · Yong Li
摘要
Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique challenges of open-ended urban spaces characterized by r...