Embodied AI TopConf · ICLR2026

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes

ICLR2026 / Benchmark and Dataset

规划/推理3D 视觉Benchmark/数据集感知
新标签打开 AlphaXiv
Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes figure
AlphaXiv 中文论文页面（可滚动查看）