# FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Model for SAR Imagery

arXiv: https://arxiv.org/abs/2602.19190 · HTML: https://mlsanity.com/paper/2602.19190/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object](https://mlsanity.com/paper/1908.05612/) (2019)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023)
- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing](https://mlsanity.com/paper/2312.12856/) (2023)
- [VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis](https://mlsanity.com/paper/2403.20213/) (2024)
- [EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues](https://mlsanity.com/paper/2412.15190/) (2024)
- [A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detection](https://mlsanity.com/paper/2312.01163/) (2023)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [Towards Vision-Language Geo-Foundation Model: A Survey](https://mlsanity.com/paper/2406.09385/) (2024)
- [STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery](https://mlsanity.com/paper/2406.09410/) (2024)
- [Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning](https://mlsanity.com/paper/2509.21976/) (2025)
- [Bootstrapping Interactive Image-Text Alignment for Remote Sensing Image Captioning](https://mlsanity.com/paper/2312.01191/) (2023)
- [Visual Position Prompt for MLLM based Visual Grounding](https://mlsanity.com/paper/2503.15426/) (2025)
- [SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding](https://mlsanity.com/paper/2504.03254/) (2025)
- [A Causal Adjustment Module for Debiasing Scene Graph Generation](https://mlsanity.com/paper/2503.17862/) (2025)
- [ATRNet-STAR: A Large Dataset and Benchmark Towards Remote Sensing Object Recognition in the Wild](https://mlsanity.com/paper/2501.13354/) (2025)
- [EarthGPT-X: A Spatial MLLM for Multi-level Multi-Source Remote Sensing Imagery Understanding with Visual Prompting](https://mlsanity.com/paper/2504.12795/) (2025)
- [Multi-Spectral Remote Sensing Image Retrieval Using Geospatial Foundation Models](https://mlsanity.com/paper/2403.02059/) (2024)
- [Object Fidelity Diffusion for Remote Sensing Image Generation](https://mlsanity.com/paper/2508.10801/) (2025)
- [Co-Training Vision Language Models for Remote Sensing Multi-task Learning](https://mlsanity.com/paper/2511.21272/) (2025)

## Built on by (most cited first, 1 of 1)

- [FUSAR-R1: A Large-Scale Reasoning Model for Intelligent Interpretation of SAR Images](https://mlsanity.com/paper/2607.16819/) (2026)

## Abstract (arXiv)

Research on the intelligent interpretation of all-weather, all-time Synthetic Aperture Radar (SAR) is crucial for advancing remote sensing applications. In recent years, although Visual Language Models (VLMs) have demonstrated strong open-world understanding capabilities on RGB images, their performance is severely limited when directly applied to the SAR field due to the complexity of the imaging mechanism, sensitivity to scattering features, and the scarcity of high-quality text corpora. To systematically address this issue, we constructed the inaugural SAR Image-Text-AlphaEarth feature triplet dataset and developed FUSAR-GPT, a VLM specifically for SAR. FUSAR-GPT innovatively introduces a geospatial baseline model as a 'world knowledge' prior and embeds multi-source remote-sensing temporal features into the model's visual backbone via 'spatiotemporal anchors', enabling dynamic compensation for the sparse representation of targets in SAR images. Furthermore, we designed a two-stage SFT strategy to decouple the knowledge injection and task execution of large models. The spatiotemporal feature embedding and the two-stage decoupling paradigm enable FUSAR-GPT to achieve state-of-the-art performance across several typical remote sensing visual-language benchmark tests, significantly outperforming mainstream baseline models by over 10%.