AI RESEARCH
Exploring Spatial Intelligence from a Generative Perspective
arXiv CS.CV
•
ArXi:2604.20570v1 Announce Type: new Spatial intelligence is essential for multimodal large language models, yet current benchmarks largely assess it only from an understanding perspective. We ask whether modern generative or unified multimodal models also possess generative spatial intelligence (GSI), the ability to respect and manipulate 3D spatial constraints during image generation, and whether such capability can be measured or improved. We