---
library_name: transformers
pipeline_tag: image-text-to-text
base_model: Qwen/Qwen2.5-VL-3B-Instruct
tags:
- remote-sensing
- earth-observation
- geospatial
- qwen2_5_vl
- grpo
---

# GeoVLM-R1

> **Disclaimer**
>
> THIS MODEL IS PROVIDED “AS IS,” WITHOUT WARRANTIES OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, ACCURACY, OR NON-INFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR THEIR AFFILIATES BE LIABLE FOR ANY DAMAGES ARISING FROM ACCESS TO OR USE OF THIS MODEL.

These models are released **without a license**. They are not open-source software.

Model weights for
[GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning](https://arxiv.org/abs/2509.25026).
Each folder is a separate Qwen2.5-VL-3B checkpoint trained for one Earth-observation task.

| Model | Task | Benchmarks |
|-------|------|------------|
| [`GeoVLM_R1_Classification`](GeoVLM_R1_Classification) | Scene classification | AID, UCMerced, WHU-RS19, BigEarthNet, fMoW |
| [`GeoVLM_R1_VQA`](GeoVLM_R1_VQA) | Visual question answering | RSVQA-LR, RSVQA-HRBEN |
| [`GeoVLM_R1_Image_caption`](GeoVLM_R1_Image_caption) | Image captioning | NWPU-Captions, RSICD, RSITMD |
| [`GeoVLM_R1_Region_Captioning`](GeoVLM_R1_Region_Captioning) | Region captioning | GeoChat region captioning, NWPU VHR-10 |
| [`GeoVLM_R1_grounding`](GeoVLM_R1_grounding) | Visual grounding (grounding description) | NWPU VHR-10 grounding |
| [`GeoVLM_R1_Refer`](GeoVLM_R1_Refer) | Referred object detection | GeoChat referring detection, NWPU VHR-10 |
| [`GeoVLM_R1_CD_Caption`](GeoVLM_R1_CD_Caption) | Change-detection captioning | LEVIR-CC, Dubai-CC, MUDS, SYSU-CC |
| [`GeoVLM_R1_xBD_object_Detection`](GeoVLM_R1_xBD_object_Detection) | xBD object detection | xBD object detection |
| [`GeoVLM_R1_xBD_refer_object_detection`](GeoVLM_R1_xBD_refer_object_detection) | xBD referred object detection | xBD referred object detection |

See each folder's `README.md` for usage. Code for training, inference and evaluation is in the
[GeoVLM-R1 Toolkit](https://github.com/IBM/GeoVLM-R1-Toolkit).

## Citation

```bibtex
@article{fiaz2025geovlmr1,
  title   = {GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning},
  author  = {Fiaz, Mustansar and Debary, Hiyam and Fraccaro, Paolo and Paudel, Danda and
             Van Gool, Luc and Khan, Fahad and Khan, Salman},
  journal = {arXiv preprint arXiv:2509.25026},
  year    = {2025}
}
```

## Contact

Mustansar Fiaz <mustansar.fiaz@ibm.com>