Grounding Isn't Knowing: Do VLMs Need Object Localization for Spatial Reasoning?
This work investigates two representative model families, LLaVA-1.5 and Qwen2.5, and provides a token-, layer-, and head-level account of how VLMs transform object grounding into spatial relations, showing that knowing where objects are is not equivalent to knowing how they relate.
Xi-Wei Liu, Yu-Long Li, Xin-Lin Zhuang et al.
· 1 citation