Add metadata and improve model card

README.md

@@ -1,3 +1,9 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+base_model: Qwen/Qwen3-8B
+---
+
 <p align="center">
   <img src="figures/logo.jpg" alt="AROMA Logo" width="120">
 </p>
@@ -5,11 +11,11 @@
 <h2 align="center"> 🧬 AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling<br>(ACL 2026 Findings)</h2>
 
 <p align="center">
-  📃 <a href="https://arxiv.org/pdf/2604.20263" target="_blank">Paper</a> • 🐙 <a href="https://github.com/blazerye/AROMA" target="_blank">Code</a> • 🗂️ <a href="https://huggingface.co/datasets/blazerye/PerturbReason" target="_blank">Datasets</a><br>
+  📃 <a href="https://huggingface.co/papers/2604.20263" target="_blank">Paper</a> • 🐙 <a href="https://github.com/blazerye/AROMA" target="_blank">Code</a> • 🗂️ <a href="https://huggingface.co/datasets/blazerye/PerturbReason" target="_blank">Datasets</a><br>
 </p>
 </p>
 
-> Please refer to our [repository](https://github.com/blazerye/AROMA) and [paper](https://arxiv.org/pdf/2604.20263) for more details.
+> Please refer to our [repository](https://github.com/blazerye/AROMA) and [paper](https://huggingface.co/papers/2604.20263) for more details.
 
 ## 🌐 Overview
 
@@ -25,4 +31,16 @@ The overall AROMA pipeline is illustrated in the figure above and is divided int
 
 - **Modeling stage.** AROMA adopts a retrieval-augmented strategy to incorporate query-relevant information, thereby providing explicit evidence cues for prediction. In addition, it jointly leverages topological representations learned from graph neural networks (GNN) and protein sequence representations encoded by ESM-2, and applies a cross-attention module to explicitly model perturbation-target gene dependencies across modalities.  
 
-- **Training stage.** AROMA first performs multimodal supervised fine-tuning (SFT), and is then further optimized with Group Relative Policy Optimization (GRPO) reinforcement learning to enhance predictive performance while generating biologically meaningful explanations.
+- **Training stage.** AROMA first performs multimodal supervised fine-tuning (SFT), and is then further optimized with Group Relative Policy Optimization (GRPO) reinforcement learning to enhance predictive performance while generating biologically meaningful explanations.
+
+## 📌 Citation
+If you find AROMA useful for your research and applications, please cite using this BibTeX:
+```bibtex
+@inproceedings{wang2026aroma,
+    title="{AROMA}: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling",
+    author="Wang, Zhenyu and Ye, Geyan and Liu, Wei and Ng, Man Tat Alexander",
+    booktitle="Findings of the Association for Computational Linguistics: ACL 2026",
+    year="2026",
+    publisher="Association for Computational Linguistics"
+}
+```