mlsanityData to 14 Oct 2026

Towards Interactive Global Geolocation Assistant

arXiv 2412.08907 ↗First posted 12 Dec 2024cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Global geolocation, which seeks to predict the geographical location of images captured anywhere in the world, is one of the most challenging tasks in the field of computer vision. In this paper, we introduce an innovative interactive global geolocation assistant named GaGA, built upon the flourishing large vision-language models (LVLMs). GaGA uncovers geographical clues within images and combines them with the extensive world knowledge embedded in LVLMs to determine the geolocations while also providing justifications and explanations for the prediction results. We further designed a novel interactive geolocation method that surpasses traditional static inference approaches. It allows users to intervene, correct, or provide clues for the predictions, making the model more flexible and practical. The development of GaGA relies on the newly proposed Multi-modal Global Geolocation (MG-Geo) dataset, a comprehensive collection of 5 million high-quality image-text pairs. GaGA achieves state-of-the-art performance on the GWS15k dataset, improving accuracy by 4.57% at the country level and 2.92% at the city level, setting a new benchmark. These advancements represent a significant leap forward in developing highly accurate, interactive geolocation systems with global applicability.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 45 of its 66 references that are in the map. First posted on arXiv 12 Dec 2024.

Builds on

45 of 66 references.

References · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2023Visual Instruction Tuningcited by 7,869
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  6. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
  7. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  9. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  10. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  11. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  12. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
33 more
  1. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captionscited by 1,005
  2. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  3. 2023DataComp: In search of the next generation of multimodal datasetscited by 644
  4. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  5. 2024Better & Faster Large Language Models via Multi-token Predictioncited by 360
  6. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  7. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  8. 2023MIMIC-IT: Multi-Modal In-Context Instruction Tuningcited by 267
  9. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 187
  10. 2022TransGeo: Transformer Is All You Need for Cross-view Image Geo-localizationcited by 168
  11. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 115
  12. 2017Revisiting IM2GPS in the Deep Learning Eracited by 80
  13. 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 70
  14. 2018CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Mapscited by 68
  15. 2023GPT4GEO: How a Language Model Sees the World's Geographycited by 68
  16. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  17. 2023PIGEON: Predicting Image Geolocationscited by 56
  18. 2023Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenescited by 55
  19. 2024VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledgecited by 50
  20. 2023Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalizationcited by 41
  21. 2024OpenStreetView-5M: The Many Roads to Global Visual Geolocationcited by 38
  22. 2024G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Modelscited by 34
  23. 2021Interpretable Semantic Photo Geolocationcited by 32
  24. 2024Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generationcited by 32
  25. 2022Cross-View Image Sequence Geo-localizationcited by 31
  26. 2024GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilotscited by 30
  27. 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Modelcited by 27
  28. 2024Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocationcited by 23
  29. 2017A Survey of Location Prediction on Twittercited by 17
  30. 2017A Neural Model for User Geolocation and Lexical Dialectologycited by 12
  31. 2022G^3: Geolocation via Guidebook Groundingcited by 12
  32. 2015Twitter User Geolocation Using a Unified Text and Network Prediction Modelcited by 4
  33. 2024GeoDecoder: Empowering Multimodal Map Understandingcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 5.

11 papers.

  1. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Modelscited by 28
  2. 2025GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalizationcited by 19
  3. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chainscited by 14
  4. 2025GAEA: A Geolocation Aware Conversational Assistantcited by 5
  5. 2025GeoArena: Evaluating Open-World Geographic Reasoning in Large Vision-Language Modelscited by 5
  6. 2025Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Viewscited by 1
  7. 2026LocationAgent: A Hierarchical Agent for Image Geolocation via Decoupling Strategy and Evidence from Parametric Knowledgecited by 1
  8. 2026Skill-Conditioned Visual Geolocation for Vision-Language Modelscited by 1
  9. 2026HoloGeo: Mitigating Landmark Bias in Geo-localization via Evidence-Driven Reasoningcited by 1
  10. 2026GTPred: Benchmarking MLLMs for Interpretable Geo-localization and Time-of-capture Predictioncited by 0
  11. 2026GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalizationcited 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. 2024Image-Based Geolocation Using Large Vision-Language Models
  3. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
  4. 2024LLMGeo: Benchmarking Large Language Models on Image Geolocation In-the-wild
  5. 2026GeoRC: A Benchmark for Geolocation Reasoning Chains
  6. 2025Assessing the Geolocation Capabilities, Limitations and Societal Risks of Generative Vision-Language Models
  7. 2025From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models
  8. 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach