mlsanityData to 14 Oct 2026

NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization

arXiv 2502.14638 ↗First posted 20 Feb 2025cs.CL cs.CVcited by 8

On the map: Multimodal LLMs / vision-language models → Embodied and 3D vision-language models

Abstract (arXiv)

Image geo-localization is the task of predicting the specific location of an image and requires complex reasoning across visual, geographical, and cultural contexts. While prior Vision Language Models (VLMs) have the best accuracy at this task, there is a dearth of high-quality datasets and models for analytical reasoning. We first create NaviClues, a high-quality dataset derived from GeoGuessr, a popular geography game, to supply examples of expert reasoning from language. Using this dataset, we present Navig, a comprehensive image geo-localization framework integrating global and fine-grained image information. By reasoning with language, Navig reduces the average distance error by 14% compared to previous state-of-the-art models while requiring fewer than 1000 training samples. Our dataset and code are available at https://github.com/SparrowZheyuan18/Navig/.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 40 references that are in the map. First posted on arXiv 20 Feb 2025.

Builds on

25 of 40 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  4. 2017Billion-scale similarity search with GPUscited by 2,497
  5. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,224
  6. 2024MiniCPM-V: A GPT-4V Level MLLM on Your Phonecited by 1,079
  7. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magiccited by 906
  8. 2023MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Actioncited by 517
  9. 2022Visual Programming: Compositional visual reasoning without trainingcited by 516
  10. 2023V*: Guided Visual Search as a Core Mechanism in Multimodal LLMscited by 482
  11. 2023GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localizationcited by 187
  12. 2020KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAcited by 125
13 more
  1. 2016PlaNet - Photo Geolocation with Convolutional Neural Networkscited by 115
  2. 2023R2Former: Unified Retrieval and Reranking Transformer for Place Recognitioncited by 102
  3. 2017Revisiting IM2GPS in the Deep Learning Eracited by 80
  4. 2024CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoningcited by 67
  5. 2022Where in the World is this Image? Transformer-based Geo-localization in the Wildcited by 58
  6. 2023Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and Scenescited by 55
  7. 2023Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalizationcited by 41
  8. 2024OpenStreetView-5M: The Many Roads to Global Visual Geolocationcited by 38
  9. 2024G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Modelscited by 34
  10. 2023What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuningcited by 28
  11. 2023Can Vision-Language Models be a Good Guesser? Exploring VLMs for Times and Location Reasoningcited by 22
  12. 2022LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injectioncited by 18
  13. 2022G^3: Geolocation via Guidebook Groundingcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbationscited by 5
  2. 2026GeoRC: A Benchmark for Geolocation Reasoning Chainscited by 4
  3. 2025Evaluation of Geolocation Capabilities of Multimodal Large Language Models and Analysis of Associated Privacy Riskscited by 3
  4. 2025Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Timecited by 3
  5. 2025Toward Reliable VLM: A Fine-Grained Benchmark and Framework for Exposure, Bias, and Inference in Korean Street Viewscited by 1
  6. 2026LocationAgent: A Hierarchical Agent for Image Geolocation via Decoupling Strategy and Evidence from Parametric Knowledgecited by 1
  7. 2026GeoAgent: Evaluating VLM Geolocalization Through Embodied Navigationcited by 0
  8. 2026Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
  2. 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
  3. 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
  4. 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
  5. 2026Locatability-Guided Adaptive Reasoning for Image Geo-Localization with Vision-Language Models
  6. 2025Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
  7. 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
  8. 2026What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization