Update README.md

README.md

@@ -17,8 +17,8 @@ tags:
 </p>
 <h4 align="center">Autoencoders as Foundation Models for 3D PDEs with Online Learning</h4>
 <p align="center">
-<a href="https://arxiv.org/abs/2408.11104">
-  <img src="https://img.shields.io/badge/arXiv-2408.11104-b31b1b?logo=arxiv" alt="Read on arXiv"/>
+<a href="https://arxiv.org/abs/2605.15284">
+  <img src="https://img.shields.io/badge/arXiv-2605.15284-b31b1b?logo=arxiv" alt="Read on arXiv"/>
 </a>
 </a>
 <a href="https://github.com/tum-pbs/Tadpole">
@@ -38,7 +38,7 @@ Tadpole distinguishes itself from existing PDE foundation models in three key as
 
 (3) Tadpole is able to process multiple downstream tasks, including autoencoding, dynamics prediction, and generative modeling.
 
-For more details, please refer to our [research paper](https://arxiv.org/abs/2408.11104):
+For more details, please refer to our [research paper](https://arxiv.org/abs/2605.15284):
 
 ## Installation and Loading Pre-trained Weights