Add model card for Nav-R2

This PR adds a comprehensive model card for the Nav-R2 model, linking it to the paper [Nav-$R^2$ Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation](https://huggingface.co/papers/2512.02400).

It includes essential metadata such as the `pipeline_tag: robotics`, `library_name: transformers`, and `license: apache-2.0`. It also incorporates relevant optional metadata like `base_model`, `datasets`, and additional descriptive `tags` for improved discoverability.

The model card features key visuals directly from the GitHub repository and provides a concise summary of the paper's abstract, adhering to the guidelines.

Please review and merge this PR if everything looks good.

README.md

@@ -0,0 +1,54 @@
+---
+license: apache-2.0
+pipeline_tag: robotics
+library_name: transformers
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+datasets:
+- Chrono666/Nav-R2-OVON-CoT-Dataset
+tags:
+- robotics
+- navigation
+- object-goal-navigation
+- vision-language-model
+- qwen
+---
+
+# Nav-$R^2$: Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation
+
+This repository contains the official implementation of the paper [Nav-$R^2$: Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation](https://huggingface.co/papers/2512.02400).
+
+Object-goal navigation in open-vocabulary settings requires agents to locate novel objects in unseen environments. Nav-$R^2$ proposes a framework that explicitly models target-environment and environment-action relationships through structured Chain-of-Thought (CoT) reasoning and a Similarity-Aware Memory. This approach enables state-of-the-art performance in localizing unseen objects efficiently while maintaining real-time inference.
+
+For more details on the code, installation, training, and evaluation, please refer to the [GitHub repository](https://github.com/AMAP-EAI/Nav-R2).
+
+## Overview
+
+<p align="center">
+ <img src="https://github.com/AMAP-EAI/Nav-R2/raw/main/figs/title.png" width="100%">
+</p>
+<p align="center">
+ <img src="https://github.com/AMAP-EAI/Nav-R2/raw/main/figs/teaser.png" width="100%">
+</p>
+
+### Pipeline and Structure
+<p align="center">
+ <img src="https://github.com/AMAP-EAI/Nav-R2/raw/main/figs/pipeline.png" width="100%">
+</p>
+
+### Results on OVON
+Here shows the results on OVON dataset. Nav-R2 is trained via **ONLY SFT** receiving **ONLY RGB observations** from **ONLY first-person view**, and achieves the best SR on the val-unseen split. 
+<p align="center">
+ <img src="https://github.com/AMAP-EAI/Nav-R2/raw/main/figs/main-results.png" width="100%">
+</p>
+
+## Citation
+If you find our work helpful or inspiring, please feel free to cite it.
+
+```bibtex
+@article{zhou2025navr2,
+  title={Nav-R2: Dual-Relation Reasoning for Generalizable Open-Vocabulary Object-Goal Navigation},
+  author={Authors names and affiliations will be added after review},
+  journal={arXiv preprint arXiv:2512.02400},
+  year={2025}
+}
+```