mlsanityData to 14 Oct 2026

GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution

arXiv 2505.21375 ↗First posted 27 May 2025cs.CVcited by 44

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

Abstract (arXiv)

Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR training data, and (2) token explosion caused by the large image size. To address data scarcity, we introduce SuperRS-VQA (avg. 8,376×8,376) and HighRS-VQA (avg. 2,000×1,912), the highest-resolution vision-language datasets in RS to date, covering 22 real-world dialogue tasks. To mitigate token explosion, our pilot studies reveal significant redundancy in RS images: crucial information is concentrated in a small subset of object-centric tokens, while pruning background tokens (e.g., ocean or forest) can even improve performance. Motivated by these findings, we propose two strategies: Background Token Pruning and Anchored Token Selection, to reduce the memory footprint while preserving key semantics.Integrating these techniques, we introduce GeoLLaVA-8K, the first RS-focused multimodal large language model capable of handling inputs up to 8K×8K resolution, built on the LLaVA framework. Trained on SuperRS-VQA and HighRS-VQA, GeoLLaVA-8K sets a new state-of-the-art on the XLRS-Bench.

Key facts. Cited by 44 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 45 of its 69 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

45 of 69 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?31 Mar
  2. 2025When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning10 Mar
  3. 2024VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding18 Jun
  4. 2024SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding14 Jun
  5. 2024VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis29 Mar
  6. 2024LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model4 Feb
  7. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain30 Jan
  8. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensing24 Nov
  9. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmark28 Jul

Other references · 36

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2023Visual Instruction Tuningcited by 7,869
  6. 2025Qwen2.5-VL Technical Reportcited by 5,587
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  11. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  12. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
24 more
  1. 2018Datasheets for Datasetscited by 1,386
  2. 2023Vision Transformers Need Registerscited by 871
  3. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 838
  4. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  5. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  6. 2024LESS: Selecting Influential Data for Targeted Instruction Tuningcited by 532
  7. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  8. 2024Long Context Transfer from Language to Visioncited by 515
  9. 2023Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Modelscited by 357
  10. 2024LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Modelscited by 353
  11. 2024InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Modelcited by 326
  12. 2023InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Compositioncited by 297
  13. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 277
  14. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 261
  15. 2024Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimizationcited by 239
  16. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 203
  17. 2024LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Imagescited by 195
  18. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  19. 2024What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functionscited by 94
  20. 2024Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Modelscited by 76
  21. 2024STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagerycited by 31
  22. 2020Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Studycited by 28
  23. 2024ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Modelscited by 24
  24. 2024OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Constructioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 35.

44 papers.

Sort:

By area:

  1. 2025Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodologycited by 69
  2. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  3. 2025GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenescited by 14
  4. 2025Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Searchcited by 11
  5. 2025A Benchmark for Ultra-High-Resolution Remote Sensing MLLMscited by 11
  6. 2025UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenescited by 10
  7. 2025SegEarth-R2: Towards Comprehensive Language-guided Segmentation for Remote Sensing Imagescited by 10
  8. 2026GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagerycited by 9
  9. 2026VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensingcited by 6
  10. 2026Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understandingcited by 4
  11. 2026Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videoscited by 4
  12. 2026Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and Taskscited by 4
32 more
  1. 2025Co-Training Vision Language Models for Remote Sensing Multi-task Learningcited by 3
  2. 2025FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensingcited by 3
  3. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Taskscited by 3
  4. 2026WeaveEarth: Structured Evidence Construction and Reasoning for Training-Free UHR Remote Sensing Understandingcited by 2
  5. 2026Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensingcited by 1
  6. 2026UAV traffic scene understanding: A regulation embedded multi-modal network and a unified benchmarkcited by 1
  7. 2026Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understandingcited by 1
  8. 2026UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensingcited by 1
  9. 2026Beyond GSD-as-Token: Continuous Scale Conditioning for Remote Sensing VLMscited by 1
  10. 2026Geospatial-Temporal Sensemaking of Remote Sensing Activity Detections with Multimodal Large Language Modelcited by 1
  11. 2026UHR-Micro: Diagnosing and Mitigating the Resolution Illusion in Earth Observation VLMscited by 1
  12. 2026Beyond Zooming: Learning Multi-Tool Visual Reasoning for Ultra-High-Resolution Remote Sensingcited by 1
  13. 2026MarsRetrieval: Benchmarking Vision-Language Models for Planetary-Scale Geospatial Retrieval on Marscited by 0
  14. 2026AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoningcited by 0
  15. 2026Beyond RGB: Benchmarking and Enhancing MLLMs for Hyperspectral Image Understanding via Training-Free Reasoning Frameworkcited by 0
  16. 2026UHR-DETR: Efficient End-to-End Small Object Detection for Ultra-High-Resolution Remote Sensing Imagerycited by 0
  17. 2026GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Imagescited by 0
  18. 2026SkyNative: A Native Multimodal Architecture for Remote Sensing Vision-Language Understandingcited by 0
  19. 2026Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?cited by 0
  20. 2026Vector Map as Language: Toward Unified Remote Sensing Vector Mappingcited by 0
  21. 2026GeoChrono: Benchmarking and Rethinking Long-Term Temporal Understanding in Remote Sensingcited by 0
  22. 2026More with Less: a Large Scale Remote Sensing VLM with a Simple Recipecited by 0
  23. 2026SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensingcited by 0
  24. 2026Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?cited by 0
  25. 2026SA-GEM: Scale-Adaptive and Geospatial Evidence-Modulated Token Pruning for Efficient Remote Sensing Large Vision-Language Modelscited by 0
  26. 2026WeaveAgent: A Two-Stage Tool-Routing Agent for Ultra-High-Resolution Remote Sensing Imagerycited by 0
  27. 2026The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understandingcited by 0
  28. 2026Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Modelscited by 0
  29. 2026RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQAcited by 0
  30. 2026Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensingcited by 0
  31. 2026Hallucination-aware Faithful Reasoning in Remote Sensingcited by 0
  32. 2026ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024RSTeller: Scaling Up Visual Language Modeling in Remote Sensing with Rich Linguistic Semantics from Openly Available Data and Large Language Models
  2. 2025GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing
  3. 2024LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation
  4. 2023RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing
  5. 2025A Vision Centric Remote Sensing Benchmark
  6. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model
  7. 2026RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation
  8. 2026BigEarthNet.txt: A Large-Scale Multi-Sensor Image-Text Dataset and Benchmark for Earth Observation