Yutong Zhong

WHERE, NOT WHAT: COMPELLING VIDEO LLMS TO LEARN GEOMETRIC CAUSALITY FOR 3D-GROUNDING

Multimodal 3D grounding has garnered considerable interest in Vision-Language Models (VLMs) \cite{yin2025spatial} for advancing spatial reasoning in complex environments. However, these models suffer from a severe "2D semantic bias" that arises from over-reliance on 2D image features for coarse loca…