Add pipeline tag and link to paper

Hi! I'm Niels, part of the community science team at Hugging Face.

I've updated the model card to include the `image-segmentation` pipeline tag, which improves discoverability on the Hub. I've also linked the model to its research paper and GitHub repository, and added the license (Apache 2.0) based on the base model. This provides better context and documentation for users and researchers.

README.md

@@ -1,16 +1,38 @@
 ---
-datasets:
-- earth-insights/EarthReason
 base_model:
 - Qwen/Qwen2.5-VL-7B-Instruct
+datasets:
+- earth-insights/EarthReason
 library_name: transformers
+pipeline_tag: image-segmentation
+license: apache-2.0
 ---
 
+# Bridging Semantics and Geometry: A Decoupled LVLM–SAM Framework for Reasoning Segmentation in Remote Sensing
+
+This repository contains the 7B model of **Think2Seg-RS**, a decoupled framework for reasoning segmentation in remote sensing (RS) imagery. 
+
+The model was introduced in the paper [Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Remote Sensing](https://huggingface.co/papers/2512.19302).
+
+## Overview
+
+Think2Seg-RS decouples high-level semantic reasoning from low-level geometric execution. It trains an LVLM prompter (based on Qwen-2.5-VL) to control a frozen Segment Anything Model (SAM2) via structured geometric prompts. Through a mask-only reinforcement learning objective, the LVLM learns to translate abstract semantic reasoning into spatially grounded actions, achieving state-of-the-art performance on the EarthReason dataset.
+
+## Resources
 
-## Bridging Semantics and Geometry: A Decoupled LVLM–SAM Framework for Reasoning Segmentation in Remote Sensing
+- **Paper:** [arXiv:2512.19302](https://huggingface.co/papers/2512.19302)
+- **Code:** [GitHub - Think2Seg-RS](https://github.com/Ricardo-XZ/Think2Seg-RS)
+- **Dataset:** [EarthReason](https://huggingface.co/datasets/earth-insights/EarthReason)
 
-This is the 7B model of [Think2Seg-RS](https://github.com/Ricardo-XZ/Think2Seg-RS), a decoupled framework for reasoning segmentation in remote sensing (RS) imagery.
+## Citation
 
-Our core idea is to decouple high-level semantic reasoning from low-level geometric execution. Specifically, we train an LVLM prompter (e.g., Qwen-2.5-VL) to control a frozen Segment Anything Model (SAM2) via structured geometric prompts. Through a result-oriented reinforcement learning objective, the LVLM learns to translate abstract semantic reasoning into spatially grounded actions, achieving state-of-the-art performance on the EarthReason dataset.
+If you find this work helpful for your research, please cite:
 
-For more details, code, and the complete framework, please visit our [GitHub repository](https://github.com/Ricardo-XZ/Think2Seg-RS).
+```bibtex
+@article{think2seg_rs_2025,
+  title={Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Remote Sensing},
+  author={Anonymous},
+  journal={arXiv preprint arXiv:2512.19302},
+  year={2025}
+}
+```