Academic or research source. Check the methodology, sample size, and whether it's been replicated.
Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
While Vision-Language Models (VLMs) exhibit exceptional 2D visual understanding, their ability to comprehend and reason about 3D space--a cornerstone of spatial intelligence--remains superficial.
Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning
TLDR
While Vision-Language Models (VLMs) exhibit exceptional 2D visual understanding, their ability to comprehend and reason about 3D space--a cornerstone of spatial intelligence--remains superficial.