Update README.md

README.md

@@ -16,7 +16,7 @@ Official release of Newt model checkpoints for the paper
 
 [Nicklas Hansen](https://nicklashansen.github.io), [Hao Su](https://cseweb.ucsd.edu/~haosu)\*, [Xiaolong Wang](https://xiaolonw.github.io)\* (UC San Diego)
 
-**Quick links:** [[Website]](https://www.nicklashansen.com/NewtWM) [[Paper]](https://arxiv.org/abs/2310.16828) [[Dataset]](https://huggingface.co/datasets/nicklashansen/tdmpc2)
+**Quick links:** [[Website]](https://www.nicklashansen.com/NewtWM) [[Paper]](https://www.nicklashansen.com/NewtWM/newt.pdf) [[Dataset]](https://huggingface.co/datasets/nicklashansen/tdmpc2)
 
 
 ## Model details
@@ -33,7 +33,7 @@ We open-source 200+ model checkpoints, including a multi-task Newt agent trained
 ### Model sources
 
 - **Repository:** [https://github.com/nicklashansen/newt](https://github.com/nicklashansen/newt)
-- **Paper:** [https://arxiv.org/abs/2310.16828](https://arxiv.org/abs/2310.16828)
+- **Paper:** [https://arxiv.org/abs/2310.16828](https://www.nicklashansen.com/NewtWM/newt.pdf)
 
 ## Uses
 
@@ -58,12 +58,11 @@ If you find our work useful, please consider citing the paper as follows:
 **BibTeX:**
 ```
 @misc{Hansen2025Newt,
-      title={Learning Massively Multitask World Models for Continuous Control}, 
-      author={Nicklas Hansen and Hao Su and Xiaolong Wang},
-      year={2025},
-      eprint={2310.16828},
-      archivePrefix={arXiv},
-      primaryClass={cs.LG}
+	title={Learning Massively Multitask World Models for Continuous Control}, 
+	author={Nicklas Hansen and Hao Su and Xiaolong Wang},
+	booktitle={Preprint},
+	url={https://www.nicklashansen.com/NewtWM},
+	year={2025}
 }
 ```