Update README.md

README.md

@@ -14,7 +14,7 @@ tags:
 
 This model corresponds to the MolDeBERTa small architecture pretrained on the 123M dataset using the contrastive MTR pretraining objective.
 
-\[[Github Repo](https://github.com/pcdslab/MolDeBERTa)\] | \[[Dataset on HuggingFace](https://huggingface.co/datasets/SaeedLab/MolDeBERTa)\] | \[[Model Collection](https://huggingface.co/collections/SaeedLab/moldeberta)\] | \[[Cite](#citation)\]
+\[[Paper](https://www.biorxiv.org/content/10.64898/2026.02.15.706011v2)\] | \[[Github Repo](https://github.com/pcdslab/MolDeBERTa)\] | \[[Dataset on HuggingFace](https://huggingface.co/datasets/SaeedLab/MolDeBERTa)\] | \[[Model Collection](https://huggingface.co/collections/SaeedLab/moldeberta)\] | \[[Cite](#citation)\]
 
 ## Abstract
 
@@ -64,7 +64,18 @@ print(embeddings.shape)
 
 ## Citation
 
-The paper is under review. As soon as it is accepted, we will update this section.
+If you use MolDeBERTa in your research, please cite:
+
+```bibtex
+@article{moldeberta2026,
+  title   = {MolDeBERTa: Foundational Model for Physicochemical and Substructure-Informed Molecular Representation Learning},
+  author  = {Oliveira, Gabriel Bianchin de and Saeed, Fahad},
+  journal = {bioRxiv},
+  year    = {2026},
+  doi     = {10.64898/2026.02.15.706011},
+  url     = {https://doi.org/10.64898/2026.02.15.706011}
+}
+```
 
 ## License