Add Arxiv ID to metadata and improve model card

Hi! I'm Niels from the Hugging Face community science team.

This PR improves the model card by:
- Adding the `arxiv` ID to the metadata to link it to the [official paper](https://huggingface.co/papers/2602.04279).
- Adding relevant tags such as `ecg`, `multimodal`, and `reasoning` to enhance searchability.
- Linking the repository to the primary dataset used (`ECG-Protocol-Guided-Grounding-CoT`).

Great work on this reasoning MLLM for ECG interpretation!

README.md

@@ -1,12 +1,18 @@
 ---
-license: apache-2.0
-language:
-- en
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
+language:
+- en
+license: apache-2.0
 pipeline_tag: image-text-to-text
 tags:
 - medical
+- ecg
+- multimodal
+- reasoning
+arxiv: 2602.04279
+datasets:
+- PKUDigitalHealth/ECG-Protocol-Guided-Grounding-CoT
 ---
 
 <div align="center">
@@ -20,6 +26,7 @@ tags:
 <a href='https://arxiv.org/pdf/2602.04279'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
 <a href='https://huggingface.co/PKUDigitalHealth/ECG-R1-8B-RL'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue'>
 <a href='https://huggingface.co/datasets/PKUDigitalHealth/ECG-Protocol-Guided-Grounding-CoT'><img src='https://img.shields.io/badge/Dataset-Huggingface-yellow'>
+<a href='http://ai.heartvoice.com.cn/ECG-R1/'><img src='https://img.shields.io/badge/Project-Page-green'></a>
 
 <p align="center">
   Jiarui Jin, Haoyu Wang, Xingliang Wu, Xiaocheng Fang, Xiang Lan, Zihan Wang<br/>
@@ -32,19 +39,15 @@ tags:
 
 ## Introduction
 
-Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using Protocol-Guided Instruction Data Generation, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with Interleaved Modality Dropout to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present Reinforcement Learning with ECG Diagnostic Evidence Rewards to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification.  Code and data are publicly available at [Github](https://github.com/PKUDigitalHealth/ECG-R1) and [HuggingFace](https://huggingface.co/datasets/PKUDigitalHealth/ECG-Protocol-Guided-Grounding-CoT), and an online platform can be accessed at [ECG-R1-Online-Platform](http://ai.heartvoice.com.cn/ECG-R1/).
-
-## Resource
-
-
-#### Paper: 📄 [Arxiv](https://arxiv.org/pdf/2602.04279)
-
-### Github: ⌨ [Github](https://github.com/PKUDigitalHealth/ECG-R1)
-
-#### Model: 🤗 [ECG-R1-8B](https://huggingface.co/PKUDigitalHealth/ECG-R1-8B-RL)
+Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using Protocol-Guided Instruction Data Generation, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with Interleaved Modality Dropout to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present Reinforcement Learning with ECG Diagnostic Evidence Rewards to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. 
 
-#### Data: 🤗 [ECG-Protocol-Guided-Grounding-CoT](https://huggingface.co/datasets/PKUDigitalHealth/ECG-Protocol-Guided-Grounding-CoT)
+## Resources
 
+- **Paper:** 📄 [Arxiv](https://arxiv.org/abs/2602.04279)
+- **Github:** ⌨ [Github](https://github.com/PKUDigitalHealth/ECG-R1)
+- **Online Platform:** 🌐 [ECG-R1 Platform](http://ai.heartvoice.com.cn/ECG-R1/)
+- **Model:** 🤗 [ECG-R1-8B](https://huggingface.co/PKUDigitalHealth/ECG-R1-8B-RL)
+- **Data:** 🤗 [ECG-Protocol-Guided-Grounding-CoT](https://huggingface.co/datasets/PKUDigitalHealth/ECG-Protocol-Guided-Grounding-CoT)
 
 ## Citation
 
@@ -63,4 +66,4 @@ If you find ECG-R1 helpful for your research and applications, please cite our p
 ```
 
 ## Acknowledgement
-We thank the authors of [PULSE](https://github.com/AIMedLab/PULSE/tree/dev), [ECG-Chat](https://github.com/YubaoZhao/ECG-Chat), [GEM](https://github.com/lanxiang1017/GEM), and [Swift](https://github.com/modelscope/ms-swift) for their publicly released models, datasets, and training codes.
+We thank the authors of [PULSE](https://github.com/AIMedLab/PULSE/tree/dev), [ECG-Chat](https://github.com/YubaoZhao/ECG-Chat), [GEM](https://github.com/lanxiang1017/GEM), and [Swift](https://github.com/modelscope/ms-swift) for their publicly released models, datasets, and training codes.