Distilling 3D Spatial Reasoning into a Lightweight Vision-Language Model with CoT

arXiv:2605.09719v1 Announce Type: cross Abstract: Large-scale 3D vision-language models (VLMs) like LLaVA-3D offer strong spatial reasoning but are difficult to deploy due to high computational costs. We propose a knowledge distillation framework that transfers spatial reasoning from a 7B teacher...