AI RESEARCH
Multimodal Language Models Cannot Spot Spatial Inconsistencies
arXiv CS.LG
•
ArXi:2604.00799v1 Announce Type: cross Spatial consistency is a fundamental property of the visual world and a key requirement for models that aim to understand physical reality. Despite recent advances, multimodal large language models (MLLMs) often struggle to reason about 3D geometry across multiple views. Rather than asking models to describe scene attributes, we