Improve model card: add metadata (tags, license) and links

This PR significantly enhances the model card by:

- Adding the `pipeline_tag: robotics` for better discoverability of embodied AI models.
- Adding the `library_name: transformers`, as indicated by the `transformers_version` in the `config.json` files, which enables automated usage snippets.
- Setting the `license` to `mit`, as explicitly stated in the GitHub repository's README.
- Including prominent links to the associated paper, the official project page, and the GitHub repository, providing a comprehensive overview for users.
- Adding an introductory description of the benchmark from the paper abstract.

These updates make the model card more informative, discoverable, and compliant with Hugging Face Hub best practices.

README.md

@@ -1,3 +1,22 @@
+---
+license: mit
+pipeline_tag: robotics
+library_name: transformers
+---
+
+# VLN-PE Benchmark Models
+
+This repository hosts models and results for the [Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities](https://huggingface.co/papers/2507.13019) benchmark.
+
+VLN-PE is a physically realistic Vision-and-Language Navigation (VLN) platform supporting humanoid, quadruped, and wheeled robots. It aims to bridge the gap between idealized assumptions and physical deployment challenges in VLN, systematically evaluating ego-centric VLN methods across different technical pipelines.
+
+*   **Project Page**: https://crystalsixone.github.io/vln_pe.github.io/
+*   **Code Repository**: https://github.com/InternRobotics/InternNav
+
+## Benchmark Results
+
+The following table presents the benchmark results for various models evaluated on the VLN-PE platform:
+
 **VLN-PE Benchmark**
 <style type="text/css">
 .tg  {border-collapse:collapse;border-spacing:0;}