Metraipolis › archive › dc_ca3d09c4c09c

AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation — arXiv:2609.18789

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18789
License (as archived)
CC0-1.0
Archived
2026-10-15T16:58:47.332Z
SHA-256 of the archived text
2019adf3b054cdff94d1f459baa9599c80eed254b4fd81ca74822676cc7f7d22
Stable URL of this page
https://metraipolis.com/documento/dc_ca3d09c4c09c

How to cite

AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation — arXiv:2609.18789 — arXiv (en), https://arxiv.org/abs/2609.18789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca3d09c4c09c (Metraipolis archive dc_ca3d09c4c09c, sha256 2019adf3b054cdff94d1f459baa9599c80eed254b4fd81ca74822676cc7f7d22)
BibTeX
@misc{dcca3d09c4c09c,
  title = {AdaGeoVLN: Selective Geometry Across Representation Depth and Navigation Time for Vision-Language Navigation — arXiv:2609.18789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca3d09c4c09c; sha256 2019adf3b054cdff94d1f459baa9599c80eed254b4fd81ca74822676cc7f7d22},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language navigation requires aligning language with visual observations while maintaining spatial understanding over time. Geometry foundation models (GFMs) expose intermediate representations throughout their hierarchy, but how navigation policies should use these features and retain historical geometric evidence remains unresolved. We introduce \method{}, a streaming VLN framework that addresses these questions across \textbf{representation depth} and \textbf{navigation time}. Hierarchical GFM--VLM fusion couples earlier, intermediate, and later GFM representations to successive policy stages instead of repeatedly injecting a terminal feature. Navigation-aware GFM memory retains historical VGGT global-attention KV states according to instruction relevance, geometric confidence, and transition novelty under a bounded per-layer budget. Retained states provide geometric context for subsequent observations before fusion with the policy. Across R2R-CE and RxR-CE, \method{} achieves strong performance using a single RGB stream without additional navigation-specific external data. Controlled ablations show that multi-depth coupling substantially outperforms repeated terminal-feature injection at matched fusion locations. Bounded navigation-aware retention preserves navigation performance while considerably reducing GFM-KV memory relative to larger-memory temporal retention. These findings support jointly examining the geometric representations exposed to the policy and the historical evidence retained for future inference. Code will be released upon acceptance at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.18789 — 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 2026-10-15T16:13:27.327Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).