15 lines
943 B
Markdown
15 lines
943 B
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
base_model:
|
||
|
|
- Qwen/Qwen2.5-VL-7B-Instruct
|
||
|
|
pipeline_tag: image-text-to-text
|
||
|
|
license: mit
|
||
|
|
---
|
||
|
|
|
||
|
|
# Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning
|
||
|
|
|
||
|
|
This repository contains the Geo-R1 model, a reasoning-centric post-training framework that unlocks geospatial reasoning in vision-language models, as introduced in the paper:
|
||
|
|
|
||
|
|
[**Geo-R1: Unlocking VLM Geospatial Reasoning with Cross-View Reinforcement Learning**](https://huggingface.co/papers/2510.00072)
|
||
|
|
|
||
|
|
Geo-R1 combines "thinking scaffolding" (supervised fine-tuning on synthetic chain-of-thought exemplars) and an "elevating" stage using GRPO-based reinforcement learning on a weakly-supervised cross-view pairing proxy. This approach enables models to connect visual cues with geographic priors and harness reasoning for accurate prediction, achieving state-of-the-art performance across various geospatial reasoning benchmarks.
|