Metraipolis › archive › dc_ab7ade240b3e
KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs — arXiv:2609.39588
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39588
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:47:43.411Z
- SHA-256 of the archived text
b696ff4d8bf6ccd22eaa02ef5d1c8bec1011c5b6dab757c6ac9bb03f08d4ff7c- Stable URL of this page
https://metraipolis.com/documento/dc_ab7ade240b3e
How to cite
KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs — arXiv:2609.39588 — arXiv (en), https://arxiv.org/abs/2609.39588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab7ade240b3e (Metraipolis archive dc_ab7ade240b3e, sha256 b696ff4d8bf6ccd22eaa02ef5d1c8bec1011c5b6dab757c6ac9bb03f08d4ff7c)
BibTeX
@misc{dcab7ade240b3e,
title = {KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMs — arXiv:2609.39588},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39588},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab7ade240b3e; sha256 b696ff4d8bf6ccd22eaa02ef5d1c8bec1011c5b6dab757c6ac9bb03f08d4ff7c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 maps. Extensive experiments reveal a fundamental divergence in how current AI models process spatial information. Instead of utilising true path integration or forming geometric survey knowledge, we find that VLMs rely almost entirely on 2D visual recognition and text-matching to bypass complex spatial reasoning. The benchmark is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39588 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T13:18:10.663Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).