Link DistillPath paper on arXiv

README.md

@@ -19,7 +19,7 @@ A 22M ViT-S/16 pathology tile encoder distilled from [UNI2-h](https://huggingfac
 
 For the ImageNet-initialized variant, see [DistillPath-IS16-UNI2h](https://huggingface.co/RamonK/DistillPath-IS16-UNI2h).
 
-**Paper:** [DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance](https://github.com/RamonKaspar/DistillPath)
+**Paper:** [DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance](https://arxiv.org/abs/2608.17872)
 Ramon Kaspar, Andrey Ignatov, Valentina Boeva. ETH Zurich.
 Published at the ECCV 2026 Workshop on Medical Foundation Models and Benchmarks (MedFM-Bench).