analiza aiqbench
This research introduces GeoVec-VLM, a model that integrates geospatial vector geometry as a native modality to overcome spatial reasoning bottlenecks in Vision-Language Models at large scales. By establishing an explicit geometric basis for interaction between visual content and language, the approach achieves significant accuracy gains and improved consistency across diverse geographic tasks. The work represents a substantive advancement in enhancing VLMs' ability to perform reliable real-world decision-making through structured spatial representations.
Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models
arXiv:2610.16769v1 Announce Type: new 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. https://github.com/TXFR/GeoVector-VLM
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
Artificial Intelligence (cs.AI)
arXiv:2610.16769 [cs.AI]
(or arXiv:2610.16769v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.16769 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 287 cuvinte
Subiecte conexe
Do Emotion Concepts Generalize Across Sources, Modalities, and Architectures in Vision-Language Models?
arXiv · 30 sept. 2026
Automating coherent long-form video generation
Google Research · 24 sept. 2026
Textual Supervision Enhances Geospatial Representations in Vision-Language Models
arXiv · 8 iun. 2026
Scaling Native Multimodal Pre-Training From Scratch
arXiv · 27 iul. 2026