mlsanityData to 14 Oct 2026

UniGeo: A Multi-modal Large Language Model for Text-Guided Cross-View Geo-Localization

arXiv 2608.26722 ↗First posted 27 Aug 2026cs.CVcited by 0

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

Abstract (arXiv)

Text-guided drone geo-localization aims to identify a target region in a large-scale image gallery from a natural-language description. Existing methods mainly formulate this task as direct matching between an open-ended text query and candidate images. However, incomplete queries and highly similar candidates often make global cross-modal matching insufficient for reliable fine-grained localization. We propose UniGeo, a unified multimodal large language model (MLLM) for text-guided drone geo-localization. Built on a shared vision-language framework, UniGeo jointly supports geo-semantic understanding, cross-view semantic generation, and candidate-level verification. Specifically, it establishes stable correspondences among local scene elements, spatial relations, and language descriptions through geo-semantic learning, and further models semantic mappings between drone and satellite views through cross-view generation. Based on these capabilities, a plug-and-play verification module performs fine-grained discrimination among highly confusable candidates. We further introduce a multi-stage training strategy that progressively learns geo-semantic understanding, cross-view generation, and candidate verification, improving adaptation to text-guided geo-localization. Experiments demonstrate consistent improvements across multiple retrieval backbones. On GeoText-1652, UniGeo improves R@10 and mAP by 13.59 and 2.83 percentage points, respectively, validating its effectiveness for fine-grained text-guided drone geo-localization.

Key facts. No citing papers in the map yet (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 53 of its 73 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

53 of 73 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Can Vision-Language Models Think from the Sky? Unifying UAV Reasoning and Generation7 Apr
  2. 2025UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding29 Jun
  3. 2025Can Multimodal Large Language Models Understand Spatial Relations?25 May

Other references · 50

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  7. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  8. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,619
  9. 2025Qwen-Image Technical Reportcited by 1,044
  10. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  11. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  12. 2021FILIP: Fine-grained Interactive Language-Image Pre-Trainingcited by 627
38 more
  1. 2021An Empirical Study of Training End-to-End Vision-and-Language Transformerscited by 271
  2. 2021Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Conceptscited by 256
  3. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 186
  4. 2026Qwen3.5-Omni Technical Reportcited by 174
  5. 2020University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localizationcited by 157
  6. 2023Grounding Language Models to Images for Multimodal Inputs and Outputscited by 131
  7. 2024Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Modelscited by 116
  8. 2023Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisationcited by 110
  9. 2024LamRA: Large Multimodal Model as Your Advanced Retrieval Assistantcited by 106
  10. 2020Each Part Matters: Local Patterns Facilitate Cross-view Geo-localizationcited by 97
  11. 2019Optimal Feature Transport for Cross-View Image Geo-Localizationcited by 91
  12. 2021E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learningcited by 85
  13. 2024Perception Tokens Enhance Visual Reasoning in Multimodal Language Modelscited by 71
  14. 2022SUES-200: A Multi-height Multi-scene Cross-view Image Benchmark Across Drone and Satellitecited by 64
  15. 2025VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documentscited by 59
  16. 2022Vision-Based UAV Self-Positioning in Low-Altitude Urban Environmentscited by 46
  17. 2022Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matchingcited by 44
  18. 2025UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editingcited by 44
  19. 2023Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matchingcited by 42
  20. 2024Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perceptioncited by 39
  21. 2024Where am I? Cross-View Geo-localization with Natural Language Descriptionscited by 38
  22. 2022Multiple-environment Self-adaptive Network for Aerial-view Geo-localizationcited by 37
  23. 2023GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglementcited by 28
  24. 2024CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentationcited by 27
  25. 2024SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localizationcited by 25
  26. 2024Game4Loc: A UAV Geo-Localization Benchmark from Game Datacited by 24
  27. 2024Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localizationcited by 17
  28. 2022Geo-Localization via Ground-to-Satellite Cross-View Image Retrievalcited by 16
  29. 2024Unified Generative and Discriminative Training for Multi-modal Large Language Modelscited by 15
  30. 2025AeroDuo: Aerial Duo for UAV-based Vision and Language Navigationcited by 13
  31. 2025AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relationscited by 10
  32. 2025Seeing through Satellite Images at Street Viewscited by 9
  33. 2024Depth-discriminative Metric Learning for Monocular 3D Object Detectioncited by 8
  34. 2024Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentationcited by 8
  35. 2025WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localizationcited by 7
  36. 2025CAMeL: Cross-modality Adaptive Meta-Learning for Text-based Person Retrievalcited by 6
  37. 2025HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Dronescited by 2
  38. 2026Turning Generators into Retrievers: Unlocking MLLMs for Natural Language-Guided Geo-Localizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization
  2. 2026SkyLink: A Large Vision-Language Model Driven Re-ranking Framework for Cross-View UAV geolocalization
  3. 2024Exploring Spatial Representation to Enhance LLM Reasoning in Aerial Vision-Language Navigation
  4. 2026S3Geo: Structure-Semantic Synergistic Learning for Cross-View Geo-Localization
  5. 2026What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization
  6. 2026Fly0: Persistent Metric Anchoring for Zero-Shot Aerial Vision-Language Navigation
  7. 2025MobileGeo: Exploring Hierarchical Knowledge Distillation for Resource-Efficient Cross-view Drone Geo-Localization
  8. 2026Multi-View Mixture-of-Experts with Vision-Language Reranking for Cross-View Object Geo-Localization