Research map / Vision-language and multimodal / Multimodal LLMs
LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, Pengfeng Xiao
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 |
|---|---|---|---|
| RS-specific alignment and curriculum training (LHRS-Bot) vs general MLLMs | LHRS-Bot · RS classification avg (7 datasets) | average accuracy (%): 44.32 -> 71.83 | Improved |
| use LHRS-Align instead of RS5M for stage-1 alignment (ablation) | LHRS-Bot · fMoW | accuracy (%): 42.68 -> 56.56 | Improved |
| use LHRS-Align instead of SkyScript for alignment (ablation) | LHRS-Bot · fMoW | accuracy (%): 31.27 -> 56.56 | Improved |
| use LHRS-Align instead of RS5M on EuroSAT and WHU-RS19 (ablation) | LHRS-Bot · EuroSAT | accuracy (%): 54.92 -> 51.40 | Hurt |
| use multi-level features with descending query allocation instead of single-level MLP (ablation) | LHRS-Bot · Visual grounding | average accuracy (%): 75.97 -> 79.90 | Improved |
| use descending [64,48,32] instead of ascending [32,48,64] queries (ablation) | LHRS-Bot · Classification | average accuracy (%): 60.68 -> 65.43 | Improved |
| use descending queries instead of identical 64 queries per level (ablation) | LHRS-Bot · VQA | average accuracy (%): 87.88 -> 90.14 | Improved |
| use token merging instead of perceiver for multi-level features (ablation) | LHRS-Bot · Classification | average accuracy (%): 65.43 -> 49.51 | Hurt |
| use single-level MLP vs perceiver multi-level on high-level tasks (ablation) | LHRS-Bot · VQA | average accuracy (%): 90.06 vs 90.14 | No clear effect |
| LHRS-Bot vs RSGPT on RSVQA-LR | LHRS-Bot · RSVQA-LR | average accuracy (%): 92.29 -> 89.19 | Hurt |
Later papers that compared with this method
4 later accepted papers report LHRS-Bot as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- SkyMoE: A Vision-Language Foundation Model for Enhancing Geospatial Interpretation with Mixture of Experts (AAAI 2026 · better on 1 of 1 shared result)
- VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis (AAAI 2025 · better on 7 of 7 shared results)
- TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data (ICLR 2025 · better on 0 of 1 shared result)
- GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields (ICCV 2025 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- mPLUG-OWL2 — mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration (CVPR 2024) · better on 2 of 2 shared results
- GeoChat — GeoChat: Grounded Large Vision-Language Model for Remote Sensing (CVPR 2024) · better on 0 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery? (CVPR 2025 · similarity 0.91)
- SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing (AAAI 2024 · similarity 0.90)
- VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing (NeurIPS 2026 · similarity 0.90)
- GeoChat: Grounded Large Vision-Language Model for Remote Sensing (CVPR 2024 · similarity 0.90)
- SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling (CVPR 2025 · similarity 0.90)
- GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution (NeurIPS 2025 · similarity 0.90)
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.
