Improve model card metadata and documentation (#1)

- Improve model card metadata and documentation (7d8f894080b02c35595cdf5a28b8ae1d1039c2be)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,24 +1,21 @@
 ---
 library_name: tedbench
-tags:
-  - protein
-  - structure
-  - fold-classification
-  - tedbench
-pipeline_tag: other
 license: bsd-3-clause
+pipeline_tag: graph-ml
+tags:
+- protein
+- structure
+- fold-classification
+- tedbench
 ---
 
 # TEDBench — Supervised from scratch (structure only)
 
 **Variant:** `miae_l`  |  **Parameters:** 339M  |  **Layers:** 24  |  **Hidden dim:** 1024  |  **Attn heads:** 16
 
-This **MiAEClassifier** was trained from scratch on TEDBench without pretraining.
+This **MiAEClassifier** was trained from scratch on TEDBench without pretraining. It is part of the research presented in the paper [Protein Fold Classification at Scale: Benchmarking and Pretraining](https://arxiv.org/abs/2605.18552).
 
-Part of the [TEDBench](https://github.com/BorgwardtLab/TEDBench) benchmark for
-protein fold classification (ICML 2026). MiAE is an SE(3)-invariant masked
-autoencoder that masks up to 90% of backbone frames and reconstructs the full
-structure with a lightweight decoder.
+MiAE is an SE(3)-invariant masked autoencoder that masks up to 90% of backbone frames and reconstructs the full structure with a lightweight decoder. It establishes a strong recipe for protein fold classification on the [TEDBench](https://github.com/BorgwardtLab/TEDBench) benchmark.
 
 ## Architecture sizes
 
@@ -50,6 +47,10 @@ model = MiAEClassifier.load_from_checkpoint("model.ckpt", weights_only=False)
 model.eval()
 ```
 
+## Links
+- **Code:** [BorgwardtLab/TEDBench](https://github.com/BorgwardtLab/TEDBench)
+- **Paper:** [arXiv:2605.18552](https://arxiv.org/abs/2605.18552)
+
 ## Citation
 
 ```bibtex
@@ -59,4 +60,4 @@ model.eval()
   booktitle={Proceedings of the 43rd International Conference on Machine Learning},
   year={2026}
 }
-```
+```