Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models 事件

Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models arXiv:2605.29074v1 Announce Type: new Abstract: Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric benchmark targeting low-level spatial intelligence in embodied 3D environments. To systematically evaluate these foundational perceptual capabilities, the benchmark includes 6 task