arXiv：cs.AI· Huang Fei, Boyi Chen, Hao Xue, Yang Yue, Yehong Xu, Xiaofang Zhou·· 16 小时前
GeoVec-VLM：将地理空间矢量几何作为视觉语言模型的原生空间模态
Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models
AI 导读
研究者提出 GeoVec-VLM，将地理空间矢量几何作为 VLM 的原生空间模态，通过保留矢量对象空间结构的几何表示与几何交互策略，让感知和推理共享几何参照。在五项空间推理任务上，该模型平均准确率较最强基线提升约 11%，并在地理迁移下保持增益、展现更强的几何一致性。
正文
Abstract:Geospatial reasoning links VLMs to real-world action and decision making. Reliable reasoning requires accurate spatial information and effective spatial representations. However, current VLMs obtain this information mainly from language and vision. At larger geographic scales, limited visual observations make it difficult to establish accurate spatial references and recover precise spatial relations. This leads to a bottleneck for VLM spatial perception and reasoning. This paper proposes that geospatial vector geometry can become a native spatial modality within a VLM and introduces GeoVec-VLM. First, we develop a structured geometry representation that preserves the spatial structure and arrangement of vector objects, building an explicit spatial basis. Second, we introduce a geometry interaction strategy that brings this basis into multimodal computation, where it interacts with visual content and language references according to the queried spatial relations. Together, these designs allow perception and reasoning to operate on shared geometric references. Across five spatial reasoning tasks, GeoVec-VLM improves mean accuracy by about 11\% relative to the strongest baseline, maintains its gains under geographic transfer, and shows greater geometric consistency. Our results show that geospatial vector geometry offers a promising internal spatial basis for VLM spatial reasoning. this https URL
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16769 [cs.AI] |
| (or arXiv:2610.16769v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16769 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fei Huang [view email]
[v1]
Mon, 12 Oct 2026 13:27:50 UTC (11,039 KB)
来源：arXiv：cs.AI · arxiv.org