1
SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision
训练多模态大模型直接内化3D空间感知，用可解释监督替代外部工具，降本增效，值得关注。
arXiv:2606.19915v1 Announce Type: new Abstract: Unlocking the spatial intelligence of multimodal large language model (MLLMs) is crucial for understan…