mlsanityData to 7 Oct 2026

Textual Supervision Enhances Geospatial Representations in Vision-Language Models

arXiv 2606.07172 ↗First posted 5 Jun 2026cs.CV cs.AI cs.CLcited by 0

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

Geospatial understanding is a critical yet underexplored dimension in the development of machine learning systems for tasks such as image geolocation and spatial reasoning. In this work, we analyze the geospatial representations acquired by three model families: vision-only architectures (e.g., ViT), vision-language models (e.g., CLIP), and large-scale multimodal foundation models (e.g., LLaVA, Qwen, and Gemma). By evaluating across image clusters, including people, landmarks, and everyday objects, grouped based on the degree of localizability, we reveal systematic gaps in spatial accuracy and show that textual supervision enhances the learning of geospatial representations. Our findings suggest the role of language as an effective complementary modality for encoding spatial context and multimodal learning as a key direction for advancing geospatial AI.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 27 of its 37 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

27 of 37 references.

References · 27

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2025Qwen2.5-VL Technical Reportcited by 5,418
  10. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  11. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  12. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
15 more
  1. 2025Gemma 3 Technical Reportcited by 1,686
  2. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  3. 2023Language Models Represent Space and Timecited by 306
  4. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  5. 2023Demystifying CLIP Datacited by 265
  6. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 185
  7. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 114
  8. 2022What do Vision Transformers Learn? A Visual Explorationcited by 75
  9. 2025Scaling Language-Free Visual Representation Learningcited by 62
  10. 2023PIGEON: Predicting Image Geolocationscited by 55
  11. 2023Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMscited by 34
  12. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 30
  13. 2024TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learningcited by 29
  14. 2024Geolocation Representation from Large Language Models are Generic Enhancers for Spatio-Temporal Learningcited by 15
  15. 2024On the Scaling Laws of Geographical Representation in Language Modelscited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
  2. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
  3. 2026What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization
  4. 2026ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models
  5. 2026Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models
  6. 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
  7. 2025Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models
  8. 2025GeoDiT: A Diffusion-based Vision-Language Model for Geospatial Understanding