Metraipolis › archive › dc_cdc2db5ab833

Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models — arXiv:2608.10278

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.10278
License (as archived)
CC0-1.0
Archived
2026-10-19T06:30:10.897Z
SHA-256 of the archived text
57bce047bcd6340f0da41046dc5639c68359e54ff3e87af1398cb9eceea73cb3
Stable URL of this page
https://metraipolis.com/documento/dc_cdc2db5ab833

How to cite

Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models — arXiv:2608.10278 — arXiv (en), https://arxiv.org/abs/2608.10278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdc2db5ab833 (Metraipolis archive dc_cdc2db5ab833, sha256 57bce047bcd6340f0da41046dc5639c68359e54ff3e87af1398cb9eceea73cb3)
BibTeX
@misc{dccdc2db5ab833,
  title = {Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models — arXiv:2608.10278},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.10278},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdc2db5ab833; sha256 57bce047bcd6340f0da41046dc5639c68359e54ff3e87af1398cb9eceea73cb3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial understanding is fundamental to embodied intelligence, underpinning applications such as robotic manipulation, embodied navigation, and autonomous driving. Although recent vision-language models (VLMs) have achieved impressive performance on spatial reasoning benchmarks, state-of-the-art approaches typically rely on additional spatial encoders or architectural modifications during inference, increasing computational cost. We introduce Space Tokens, a lightweight, architecture-agnostic framework that equips VLMs with explicit continuous spatial representations without requiring additional inference-time modules. By distilling scene-level 3D geometry and object-centric spatial attributes into continuous latent tokens, our method enables these modalities to be directly incorporated into a chain-of-thought reasoning process, thereby improving the VLM's spatial reasoning capabilities. At the same time, the learned representations can be explicitly decoded to verify that they encode meaningful geometric information, while the unified token interface remains extensible to additional modalities. Experiments on VSI-Bench improve Qwen3-VL-8B by 4.3% and SenseNova-SI-1.3 by 1.3%, while achieving state-of-the-art performance on object size (79.2%) and room size estimation (75.7%). These results demonstrate that continuous spatial tokens provide an effective, interpretable, and computationally efficient mechanism for integrating geometric reasoning into large vision-language models.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.10278 — 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 2026-10-19T06:25:27.236Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).