Research map / Vision-language and multimodal / Multimodal LLMs
RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning
Huiyang Hu, Peijin Wang, Yingchao Feng, Kaiwen Wei, Wenxin Yin, Wenhui Diao, Mengyu Wang, Hanbo Bi, Kaiyue Kang, Tong Ling, Kun Fu, Xian Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RingMo-Agent instead of AerialVLN + GSM | navigation model · CityNav Test Unseen | SR: 6.72 -> 21.15 | Improved |
| use RingMo-Agent instead of AerialVLN + GSM | navigation model · CityNav Test Unseen | NE: 85.1 -> 64.2 | Improved |
| use RingMo-Agent instead of SkyAgent | planning model · SkyAgent-Plan3k ShangHai | SPICE: 26.53 -> 31.68 | Improved |
| use RingMo-Agent instead of SkyAgent | planning model · SkyAgent-Plan3k Residence | SPICE: 24.29 -> 37.68 | Improved |
| use RingMo-Agent instead of SkyAgent | planning model · SkyAgent-Plan3k ShangHai | BLEU-1: 40.87 -> 37.33 | Hurt |
| fine-tune RingMo-Agent instead of using SkySenseGPT | relation reasoning · FIT-RS | F1-score: 74.33 -> 75.34 | Improved |
| instruction-tune RingMo-Agent vs zero-shot GPT-4o | instruction decomposition · ReCon1M-DEC | mAP@50: 0.50 -> 24.20 | Improved |
| use RingMo-Agent instead of RS-LLaVA | VQA · RSVQA-LR | Avg. accuracy: 92.07 -> 90.30 | Hurt |
| use RingMo-Agent instead of SkySenseGPT zero-shot | VQA · RSVQA-HR | Avg. accuracy: 76.64 -> 79.58 | Improved |
| use RingMo-Agent instead of RingMoGPT zero-shot | captioning · NWPU-Captions | METEOR: 20.90 -> 18.81 | Hurt |
| use RingMo-Agent instead of RingMoGPT zero-shot | classification · UCMerced-LandUse | accuracy: 86.48 -> 86.52 | Improved |
| use RingMo-Agent instead of RingMoGPT zero-shot | classification · WHU-RS19 | accuracy: 97.71 -> 95.28 | Hurt |
Closest papers by meaning
- Asking like Socrates: Socrates helps VLMs understand remote sensing images (CVPR 2026 · similarity 0.90)
- SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts (AAAI 2026 · similarity 0.89)
- Towards Faithful Reasoning in Remote Sensing: A Perceptually-Grounded GeoSpatial Chain-of-Thought for Vision-Language Models (ICLR 2026 · similarity 0.88)
- Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding (ICML 2026 · similarity 0.88)
- RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow (AAAI 2026 · similarity 0.87)
- VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
