KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs

Excerpt

arXiv:2609.39588v1 Announce Type: cross Abstract: We push the frontier of large-scale spatial intelligence in Vision-Language Models (VLMs) and introduce the first benchmark that probes geographical layout understanding from real-world videos, spanning up to 1km distances. Inspired by the cognitive science literature, we evaluate models against the hierarchical stages of human spatial awareness: anchoring via landmarks, connecting them through routes, and integrating these into global mental map