mlsanityData to 14 Oct 2026

A Satellite-Ground Synergistic Large Vision-Language Model System for Earth Observation

arXiv 2507.05731 ↗First posted 8 Jul 2025cs.NI cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Recently, large vision-language models (LVLMs) unleash powerful analysis capabilities for low Earth orbit (LEO) satellite Earth observation images in the data center. However, fast satellite motion, brief satellite-ground station (GS) contact windows, and large size of the images pose a data download challenge. To enable near real-time Earth observation applications (e.g., disaster and extreme weather monitoring), we should explore how to deploy LVLM in LEO satellite networks, and design SpaceVerse, an efficient satellite-ground synergistic LVLM inference system. To this end, firstly, we deploy compact LVLMs on satellites for lightweight tasks, whereas regular LVLMs operate on GSs to handle computationally intensive tasks. Then, we propose a computing and communication co-design framework comprised of a progressive confidence network and an attention-based multi-scale preprocessing, used to identify on-satellite inferring data, and reduce data redundancy before satellite-GS transmission, separately. We implement and evaluate SpaceVerse on real-world LEO satellite constellations and datasets, achieving a 31.2% average gain in accuracy and a 51.2% reduction in latency compared to state-of-the-art baselines.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 44 of its 76 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

44 of 76 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  5. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  6. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 797
  7. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 623
  8. 2023RemoteCLIP: A Vision Language Foundation Model for Remote Sensingcited by 363
  9. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  10. 2023SpectralGPT: Spectral Remote Sensing Foundation Modelcited by 252
  11. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Modelscited by 217
  12. 2023RSGPT: A Remote Sensing Vision Language Model and Benchmarkcited by 207
32 more
  1. 2020RSVQA: Visual Question Answering for Remote Sensing Datacited by 203
  2. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 184
  3. 2024SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Modelcited by 113
  4. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  5. 2023Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networkscited by 95
  6. 2020A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagerycited by 88
  7. 2022Petals: Collaborative Inference and Fine-tuning of Large Modelscited by 87
  8. 2024NetLLM: Adapting Large Language Models for Networkingcited by 78
  9. 2024AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networkscited by 64
  10. 2024SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 62
  11. 2024Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 49
  12. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 39
  13. 2023FedSN: A Federated Learning Framework over Heterogeneous LEO Satellite Networkscited by 38
  14. 2025HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Modelscited by 31
  15. 2024Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Modelscited by 27
  16. 2024FedAC: An Adaptive Clustered Federated Learning Framework for Heterogeneous Datacited by 25
  17. 2025LEO-Split: A Semi-Supervised Split Learning Framework over LEO Satellite Networkscited by 22
  18. 2024SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Frameworkcited by 21
  19. 2024IC3M: In-Car Multimodal Multi-object Monitoring for Abnormal Status of Both Driver and Passengerscited by 20
  20. 2024MERIT: Multimodal Wearable Vital Sign Waveform Monitoringcited by 16
  21. 2025LCFed: An Efficient Clustered Federated Learning Framework for Heterogeneous Datacited by 15
  22. 2025HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systemscited by 15
  23. 2024SATSense: Multi-Satellite Collaborative Framework for Spectrum Sensingcited by 14
  24. 2024PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questionscited by 14
  25. 2021Seeing Through Clouds in Satellite Imagescited by 13
  26. 2025Constructing 4D Radio Map in LEO Satellite Networks with Limited Samplescited by 13
  27. 2024Sums: Sniffing Unknown Multiband Signals under Low Sampling Ratescited by 12
  28. 2021RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Networkcited by 11
  29. 2024UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptationcited by 10
  30. 2024LEO Satellite Networks Assisted Geo-distributed Data Processingcited by 10
  31. 2024S4: Self-Supervised Sensing Across the Spectrumcited by 5
  32. 2022The Digital Divide in Canada and the Role of LEO Satellites in Bridging the Gapcited by 3

Built on by

Cited by year (2026 to 14 Oct)

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

3 papers.

  1. 2025Enabling Near-realtime Remote Sensing via Satellite-Ground Collaboration of Large Vision-Language Modelscited by 1
  2. 2025An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domaincited by 0
  3. 2026Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Taskscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Summarize First, Download Later: Onboard VLMs for Bandwidth-Efficient Earth Observation
  2. 2024LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation
  3. 2025SATGround: A Spatially-Aware Approach for Visual Grounding in Remote Sensing
  4. 2026More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe
  5. 2026SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Satellite Networks
  6. 2026LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
  7. 2026OmniEarth: A Benchmark for Evaluating Vision-Language Models in Geospatial Tasks
  8. 2026RemoteShield: Enable Robust Multimodal Large Language Models for Earth Observation