mlsanityData to 7 Oct 2026

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model

arXiv 2406.18572 ↗First posted 3 Jun 2024cs.CV cs.LGcited by 27

On the map: LLM reasoning → Spatial and embodied reasoning

also in 1 more
Abstract (arXiv)

This work tackles the problem of geo-localization with a new paradigm using a large vision-language model (LVLM) augmented with human inference knowledge. A primary challenge here is the scarcity of data for training the LVLM - existing street-view datasets often contain numerous low-quality images lacking visual clues, and lack any reasoning inference. To address the data-quality issue, we devise a CLIP-based network to quantify the degree of street-view images being locatable, leading to the creation of a new dataset comprising highly locatable street views. To enhance reasoning inference, we integrate external knowledge obtained from real geo-localization games, tapping into valuable human inference capabilities. The data are utilized to train GeoReasoner, which undergoes fine-tuning through dedicated reasoning and location-tuning stages. Qualitative and quantitative evaluations illustrate that GeoReasoner outperforms counterpart LVLMs by more than 25% at country-level and 38% at city-level geo-localization tasks, and surpasses StreetCLIP performance while requiring fewer training resources. The data and code are available at https://github.com/lingli1996/GeoReasoner.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 26 of its 42 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

26 of 42 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023GPT-4 Technical Reportcited by 18,132
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  8. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  9. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  10. 2022Reasoning with Language Model Prompting: A Surveycited by 251
  11. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
  12. 2022Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizerscited by 204
14 more
  1. 2024MMT-Bench: A Comprehensive Multimodal Benchmark for Evaluating Large Vision-Language Models Towards Multitask AGIcited by 192
  2. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 185
  3. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 166
  4. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  5. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 114
  6. 2017Revisiting IM2GPS in the Deep Learning Eracited by 79
  7. 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 69
  8. 2018CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Mapscited by 68
  9. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  10. 2023Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenescited by 55
  11. 2023Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalizationcited by 41
  12. 2021Interpretable Semantic Photo Geolocationcited by 32
  13. 2023Retrieval-based Knowledge Augmented Vision Language Pre-trainingcited by 17
  14. 2022G^3: Geolocation via Guidebook Groundingcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 15; 2026: 10.

27 papers.

Sort:

By area:

  1. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 27
  2. 2025GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalizationcited by 18
  3. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chainscited by 14
  4. 2025TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Actioncited by 13
  5. 2024Towards Interactive Global Geolocation Assistantcited by 11
  6. 2025A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Sciencecited by 11
  7. 2026Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalizationcited by 8
  8. 2025Hyperlocal disaster damage assessment using bi-temporal street-view imagery and pre-trained vision modelscited by 7
  9. 2025OFFSIDE: Benchmarking Unlearning Misinformation in Multimodal Large Language Modelscited by 7
  10. 2025Better Reasoning with Less Data: Enhancing VLMs Through Unified Modality Scoringcited by 6
  11. 2025GAEA: A Geolocation Aware Conversational Assistantcited by 5
  12. 2025Enhancing Large Vision Model in Street Scene Semantic Understanding through Leveraging Posterior Optimization Trajectorycited by 4
15 more
  1. 2025VICI: VLM-Instructed Cross-view Image-localisationcited by 3
  2. 2025LM-mixup: Text Data Augmentation via Language Model based Mixupcited by 3
  3. 2025Towards General Urban Monitoring with Vision-Language Models: A Review, Evaluation, and a Research Agendacited by 2
  4. 2026BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusioncited by 2
  5. 2026Urban Socio-Semantic Segmentation with Vision-Language Reasoningcited by 2
  6. 2024Advancements in Visual Language Models for Remote Sensing: Datasets, Capabilities, and Enhancement Techniquescited by 1
  7. 2025MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalizationcited by 1
  8. 2025Street-Level Geolocalization Using Multimodal Large Language Models and Retrieval-Augmented Generationcited by 1
  9. 2026HierLoc: Hyperbolic Entity Embeddings for Hierarchical Visual Geolocationcited by 1
  10. 2026DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoEcited by 1
  11. 2026Interpretable Perception and Reasoning for Audiovisual Geolocationcited by 1
  12. 2026Where Do Images Come From? Analyzing Captions to Geographically Profile Datasetscited by 0
  13. 2026DamageArbiter: A Multimodal Arbitration Framework for Disaster Damage Assessment from Street-View Imagerycited by 0
  14. 2026GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalizationcited by 0
  15. 2026Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
  2. 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
  3. 2026m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning
  4. 2025GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
  5. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
  6. 2026Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models
  7. 2026GTPred: Benchmarking MLLMs for Interpretable Geo-localization and Time-of-capture Prediction
  8. 2025From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models