Author name: Jiang Zhang, Shijie Zhou, Bangya Liu, Achuta Kadambi, Zhiwen Fan

arXiv:2603.27437v2 Announce Type: replace
Abstract: Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture f…

arXiv:2603.27437v1 Announce Type: new
Abstract: Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-…