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_Region_Captioning
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.
This model is released without a license. It is not open-source software.
Model description
GeoVLM_R1_Region_Captioning is the Region captioning checkpoint of GeoVLM-R1, from the paper
GeoVLM-R1: Reinforcement Fine-Tuning for Improved Remote Sensing Reasoning.
- Architecture:
Qwen2_5_VLForConditionalGeneration(3B parameters, bfloat16) - Training: Qwen2.5-VL-3B-Instruct, then supervised fine-tuning on EarthDial-Instruct, then
GRPO reinforcement fine-tuning with task-aware rewards on
GRPO_GeoChat_region_caption_refined.jsonl - Task: Region captioning
- Benchmarks: GeoChat region captioning, NWPU VHR-10
GeoVLM-R1 has one checkpoint per task. All 9 are in ibm-research/GeoVLM-R1.
Usage
import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
model_path = "path/to/GeoVLM_R1_Region_Captioning"
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
model_path, torch_dtype=torch.bfloat16, device_map="auto").eval()
processor = AutoProcessor.from_pretrained(model_path)
messages = [{
"role": "user",
"content": [
{"type": "image", "image": "example.png", "resized_height": 448, "resized_width": 448},
{"type": "text", "text": "Describe this image."},
],
}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
images, videos = process_vision_info(messages)
inputs = processor(text=[text], images=images, videos=videos,
padding=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=128)
print(processor.batch_decode([o[len(i):] for i, o in zip(inputs.input_ids, out)],
skip_special_tokens=True)[0])
To run the benchmark, use GeoVLM_inference/generate_inference_region_captioning.py from the
GeoVLM-R1 Toolkit with --model_path path/to/GeoVLM_R1_Region_Captioning.
Citation
@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