AI RESEARCH
SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning
arXiv CS.CV
•
ArXi:2604.17385v1 Announce Type: new Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal large language models (MLLMs) often exhibit fragile reasoning traces in spatial intelligence tasks that involve consistent spatial state recognition. We argue that these failures stem from a mismatch between the spatial recognition mechanism and the text-only reasoning behavior of these MLLMs.