mlsanityData to 7 Oct 2026

IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence

arXiv 2507.06993 ↗First posted 9 Jul 2025cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Map applications are still largely point-and-click, making it difficult to ask map-centric questions or connect what a camera sees to the surrounding geospatial context with view-conditioned inputs. We introduce IMAIA, an interactive Maps AI Assistant that enables natural-language interaction with both vector (street) maps and satellite imagery, and augments camera inputs with geospatial intelligence to help users understand the world. IMAIA comprises two complementary components. Maps Plus treats the map as first-class context by parsing tiled vector/satellite views into a grid-aligned representation that a language model can query to resolve deictic references (e.g., ``the flower-shaped building next to the park in the top-right''). Places AI Smart Assistant (PAISA) performs camera-aware place understanding by fusing image--place embeddings with geospatial signals (location, heading, proximity) to ground a scene, surface salient attributes, and generate concise explanations. A lightweight multi-agent design keeps latency low and exposes interpretable intermediate decisions. Across map-centric QA and camera-to-place grounding tasks, IMAIA improves accuracy and responsiveness over strong baselines while remaining practical for user-facing deployments. By unifying language, maps, and geospatial cues, IMAIA moves beyond scripted tools toward conversational mapping that is both spatially grounded and broadly usable.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 9 Jul 2025.

Builds on

23 of 36 references.

References · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2024GPT-4o System Cardcited by 4,467
  4. 2024Depth Anything V2cited by 1,385
  5. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  6. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  7. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  8. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  9. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 297
  10. 2024A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systemscited by 170
  11. 2024The All-Seeing Project V2: Towards General Relation Comprehension of the Open Worldcited by 90
  12. 2023Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Searchcited by 74
11 more
  1. 2023GPT4GEO: How a Language Model Sees the World's Geographycited by 68
  2. 2021TAG: Gradient Attack on Transformer-based Language Modelscited by 63
  3. 2024TravelAgent: An AI Assistant for Personalized Travel Planningcited by 38
  4. 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understandingcited by 37
  5. 2024How Can Large Language Models Understand Spatial-Temporal Data?cited by 31
  6. 2024Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Frameworkcited by 19
  7. 2024Florence-VL: Enhancing Vision-Language Models with Generative Vision Encoder and Depth-Breadth Fusioncited by 18
  8. 2024Comparing Traditional and LLM-based Search for Image Geolocationcited by 10
  9. 2024Distilling Adversarial Robustness Using Heterogeneous Teacherscited by 3
  10. 2023Smooth and Stepwise Self-Distillation for Object Detectioncited by 2
  11. 2024Certifying Adapters: Enabling and Enhancing the Certification of Classifier Adversarial Robustnesscited by 2

Built on by

Not cited yet.