mlsanityData to 14 Oct 2026

Foundation Models for Remote Sensing: An Analysis of MLLMs for Object Localization

arXiv 2504.10727 ↗First posted 14 Apr 2025cs.CVcited by 3

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

Abstract (arXiv)

Multimodal large language models (MLLMs) have altered the landscape of computer vision, obtaining impressive results across a wide range of tasks, especially in zero-shot settings. Unfortunately, their strong performance does not always transfer to out-of-distribution domains, such as earth observation (EO) imagery. Prior work has demonstrated that MLLMs excel at some EO tasks, such as image captioning and scene understanding, while failing at tasks that require more fine-grained spatial reasoning, such as object localization. However, MLLMs are advancing rapidly and insights quickly become out-dated. In this work, we analyze more recent MLLMs that have been explicitly trained to include fine-grained spatial reasoning capabilities, benchmarking them on EO object localization tasks. We demonstrate that these models are performant in certain settings, making them well suited for zero-shot scenarios. Additionally, we provide a detailed discussion focused on prompt selection, ground sample distance (GSD) optimization, and analyzing failure cases. We hope that this work will prove valuable as others evaluate whether an MLLM is well suited for a given EO localization task and how to optimize it.

Key facts. Cited by 3 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 23 of its 36 references that are in the map. First posted on arXiv 14 Apr 2025.

Builds on

23 of 36 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation data31 Jan
  2. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
  3. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul

Other references · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  9. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  10. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  11. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  12. 2021Grounded Language-Image Pre-trainingcited by 1,156
8 more
  1. 2024DoRA: Weight-Decomposed Low-Rank Adaptationcited by 758
  2. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
  3. 2023GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interestcited by 302
  4. 2024OLMoE: Open Mixture-of-Experts Language Modelscited by 301
  5. 2024TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Datacited by 70
  6. 2024What's in the Image? A Deep-Dive into the Vision of Vision Language Modelscited by 68
  7. 2020RarePlanes: Synthetic Data Takes Flightcited by 48
  8. 2025A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challengescited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensingcited by 6
  2. 2025VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systemscited by 0
  3. 2026Do Open-Vocabulary Detectors Transfer to Aerial Imagery? A Comparative Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?
  2. 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
  3. 2025A Vision Centric Remote Sensing Benchmark
  4. 2025SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing
  5. 2026Where Do Vision-Language Models Fail? World Scale Analysis for Image Geolocalization
  6. 2025Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives
  7. 2026From Coordinates to Candidate Regions: Temporal Change Localization via Region Selection in Remote Sensing Multimodal LLMs
  8. 2025Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales