Improve model card: add pipeline tag and relevant links

README.md

@@ -1,21 +1,24 @@
 ---
+datasets:
+- HC18
 license: cc-by-nc-4.0
+metrics:
+- f1
+- auroc
+pipeline_tag: zero-shot-image-classification
 tags:
 - medical
 - ultrasound
 - vision
 - knowledge-distillation
-metrics:
-- f1
-- auroc
-datasets:
-- HC18
 ---
 
 # MobileFetalCLIP
 
 **Selective Repulsive Knowledge Distillation for Mobile Fetal Ultrasound Analysis**
 
+[Project Website](https://numansaeed.com/MobileFetalCLIP/) | [Paper](https://huggingface.co/papers/2603.05421) | [GitHub Repository](https://github.com/numanai/MobileFetalCLIP)
+
 MobileFetalCLIP is a highly efficient foundation model designed specifically for fetal ultrasound analysis on point-of-care, low-resource devices (like smartphones). It achieves this by distilling knowledge from a massive 427M parameter teacher model into a tiny 11.4M parameter student model using a novel technique called **Selective Repulsive Knowledge Distillation**.
 
 Despite being **26× smaller** and **24× faster**, MobileFetalCLIP *surpasses* its massive teacher on standard validity benchmarks (HC18) and retains 97-98% of linear probing performance across tasks.
@@ -35,12 +38,12 @@ Despite being **26× smaller** and **24× faster**, MobileFetalCLIP *surpasses*
 
 ## Usage
 
-Please refer to the official GitHub repository for inference scripts and model loading instructions:
+Please refer to the official GitHub repository for installation instructions, dataset preparation, and inference scripts:
 🔗 **[GitHub: numanai/MobileFetalCLIP](https://github.com/numanai/MobileFetalCLIP)**
 
 ## Citation
 
-If you find this model or codebase useful for your research, please cite our arXiv preprint:
+If you find this model or codebase useful for your research, please cite the paper:
 
 ```bibtex
 @article{saeed2026mobilefetalclip,
@@ -50,3 +53,4 @@ If you find this model or codebase useful for your research, please cite our arX
   journal   = {arXiv preprint arXiv:2603.05421},
   year      = {2026}
 }
+```