Metraipolis › archive › dc_c478f56ae303

Probing Spatial State Representations in Visual Foundation Models — arXiv:2610.40636

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40636
License (as archived)
CC0-1.0
Archived
2026-10-31T06:15:00.863Z
SHA-256 of the archived text
a68340d18020f18ccbbad51150ec17a3b29f2466b5b3ec53b44f691365664fe0
Stable URL of this page
https://metraipolis.com/documento/dc_c478f56ae303

How to cite

Probing Spatial State Representations in Visual Foundation Models — arXiv:2610.40636 — arXiv (en), https://arxiv.org/abs/2610.40636 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c478f56ae303 (Metraipolis archive dc_c478f56ae303, sha256 a68340d18020f18ccbbad51150ec17a3b29f2466b5b3ec53b44f691365664fe0)
BibTeX
@misc{dcc478f56ae303,
  title = {Probing Spatial State Representations in Visual Foundation Models — arXiv:2610.40636},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40636},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c478f56ae303; sha256 a68340d18020f18ccbbad51150ec17a3b29f2466b5b3ec53b44f691365664fe0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40636. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

An observer sees only part of the surrounding world, yet must keep track of what lies beyond the current view. Spatial perception therefore involves more than recognizing individual images: it calls for a persistent spatial state that is updated under self-motion and used to guide action. Do visual foundation models provide representations that support such a state? We study this question through four levels of spatial capability---spatial structure, object persistence, predictive spatial update, and actionability---using frozen-feature probes on ten representations under streaming egocentric observations of static indoor environments. The resulting capability profiles vary across tasks, network layers, and prefix lengths: strong readout of the visible scene does not ensure accurate object persistence or future-feature retrieval. Matched controls separate readout accuracy from reliance on visual history and motion. Native future prediction retains recoverable spatial structure, but a spatial reader trained on real features does not transfer to predicted features unchanged. Finally, goal-dependent candidate selection does not establish reliable continuous action utility: predicted actions respond to goal changes, yet supplying the correct goal does not reliably improve progress. Across the four levels, object persistence and actionability build on camera-pose readout, whereas feature prediction builds on visible-scene readout. Together, these findings motivate evaluating spatial representations not only by what can be decoded from them, but by whether that information is maintained beyond observation, updated predictively, and used for goal-directed action.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.40636 — 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 2026-10-31T06:07:08.783Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).