Update model card metadata and add GitHub link

README.md

@@ -1,23 +1,25 @@
 ---
-license: apache-2.0
-language:
-  - en
 base_model: Qwen/Qwen3.5-9B
-tags:
-  - embodied-ai
-  - spatial-intelligence
-  - vision-language
-  - tvr
 datasets:
-  - TVRBench/tvr-sft-va
-pipeline_tag: image-text-to-text
-arxiv: 2606.01247
+- TVRBench/tvr-sft-va
+language:
+- en
+license: apache-2.0
+pipeline_tag: robotics
+library_name: transformers
+tags:
+- embodied-ai
+- spatial-intelligence
+- vision-language
+- tvr
 ---
 
 # TVR-Qwen3.5-9B-VA-SFT-RL
 
 Best-performing model from the paper **"Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?"** [[arXiv]](https://arxiv.org/abs/2606.01247).
 
+Code: [https://github.com/aim-uofa/TVRBench](https://github.com/aim-uofa/TVRBench)
+
 ## Model Description
 
 Fine-tuned from [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for **Target Viewpoint Reproduction (TVR)** — the agent receives a target image and navigates in a 3D indoor environment to reproduce the exact viewpoint through active exploration.
@@ -30,7 +32,7 @@ Fine-tuned from [Qwen3.5-9B](https://huggingface.co/Qwen/Qwen3.5-9B) for **Targe
 
 ## Usage
 
-See the [TVRBench repository](https://github.com/aim-uofa/TVRBench) for evaluation instructions.
+Evaluation requires setting up the AI2-THOR simulator. See the [TVRBench repository](https://github.com/aim-uofa/TVRBench) for detailed evaluation instructions and scripts to serve the model using vLLM.
 
 ## Citation
 
@@ -44,4 +46,4 @@ See the [TVRBench repository](https://github.com/aim-uofa/TVRBench) for evaluati
       primaryClass={cs.CV},
       url={https://arxiv.org/abs/2606.01247}, 
 }
-```
+```