Metraipolis › archive › dc_aab775577348

Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation — arXiv:2609.29934

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.29934
License (as archived): CC0-1.0
Archived: 2026-10-08T06:44:38.849Z
SHA-256 of the archived text: 955073e7c0517813399145d1fbddb9335aadf9f1db83d706f0d7855618bfd68b
Stable URL of this page: https://metraipolis.com/documento/dc_aab775577348

How to cite

Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation — arXiv:2609.29934 — arXiv (en), https://arxiv.org/abs/2609.29934 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aab775577348 (Metraipolis archive dc_aab775577348, sha256 955073e7c0517813399145d1fbddb9335aadf9f1db83d706f0d7855618bfd68b)

BibTeX

@misc{dcaab775577348,
  title = {Beyond Spatial Benchmarks: From Spatial Reasoning to Navigation — arXiv:2609.29934},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29934},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aab775577348; sha256 955073e7c0517813399145d1fbddb9335aadf9f1db83d706f0d7855618bfd68b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29934. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Does progress on spatial reasoning benchmarks translate into better navigation? Existing benchmarks test isolated inferences from images or videos, with little connection to downstream navigation. Our analysis reveals a gap between benchmark-oriented spatial specialization and navigation performance, and shows how aligning spatial supervision with navigation goals, phases, and decision learning improves navigation. Guided by these findings, we build \textsc{Spatial-Nav-100K} and fine-tune in two stages, \textit{i.e.} first learning a shared spatial-navigation foundation, and then specializing each phase with the abilities it relies on. We further introduce Spatial-NPD, where a teacher conditioned on spatial priors produces grounded action preferences and distills them into a student policy, so no explicit spatial reasoning is needed at inference. With 45 A100 GPU-hours of policy training, our 8B model reaches SR/SPL of 77.4/35.4 on HM3D-v0.2, 60.2/30.5 on HM3D-v0.1, and 47.9/20.6 on train-unseen MP3D. It outperforms several systems that rely on closed-source models or thousands of GPU-hours of training, at 148 ms per action step. All code and datasets will be publicly available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.29934 — 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 2026-10-08T06:09:29.897Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).