Add robotics tag, library metadata, and project link

README.md

@@ -1,21 +1,21 @@
 ---
-license: cc-by-4.0
+base_model:
+- Qwen/Qwen3-VL-8B-Instruct
 datasets:
 - teetone/RoboReward
 language:
 - en
-base_model:
-- Qwen/Qwen3-VL-8B-Instruct
+license: cc-by-4.0
+library_name: transformers
+pipeline_tag: robotics
 ---
 
-
 # RoboReward 8B
 
-**Paper:** [https://arxiv.org/abs/2601.00675](https://arxiv.org/abs/2601.00675)
+[**Project Page**](https://crfm.stanford.edu/helm/robo-reward-bench) | [**Paper**](https://huggingface.co/papers/2601.00675)
 
 RoboReward provides **general-purpose vision-language reward model for robotics**, trained on the [RoboReward dataset](https://huggingface.co/datasets/teetone/RoboReward) with **Qwen-3 VL** to predict **discrete end-of-episode progress rewards** from real-robot rollout videos.  
 
-
 ## Usage
 
 ### Purpose