Update README.md

README.md

@@ -10,34 +10,43 @@ tags:
 
 # MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
 
-This is the official model repository of the preprint paper \
+This is the official **model** repository of the preprint paper \
 *[MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers](https://arxiv.org/abs/2402.02263)* \
-by [Yatong Bai](https://bai-yt.github.io), [Mo Zhou](https://cdluminate.github.io), [Vishal M. Patel](https://engineering.jhu.edu/faculty/vishal-patel), and [Somayeh Sojoudi](https://www2.eecs.berkeley.edu/Faculty/Homepages/sojoudi.html).
+by [Yatong Bai](https://bai-yt.github.io), [Mo Zhou](https://cdluminate.github.io), [Vishal M. Patel](https://engineering.jhu.edu/faculty/vishal-patel),
+and [Somayeh Sojoudi](https://www2.eecs.berkeley.edu/Faculty/Homepages/sojoudi.html) in Transactions on Machine Learning Research.
+
+<center>
+  <img src="main_figure.png" alt="MixedNUTS Results" title="Results" width="800"/>
+</center>
 
 **TL;DR:** MixedNUTS balances clean data classification accuracy and adversarial robustness without additional training
 via a mixed classifier with nonlinear base model logit transformations.
 
+## Model Checkpoints
+
+MixedNUTS is a training-free method that has no additional neural network components other than its base classifiers.
+
+All robust base classifiers used in the main results of our paper are available on [RobustBench](https://robustbench.github.io)
+and can be downloaded automatically via the RobustBench API.
+
 Here, we provide the download links to the standard base classifiers used in the main results.
-| Dataset | Link |
+
+| Dataset   | Link  |
 |-----------|-------|
-| CIFAR-10 | [Download](https://huggingface.co/Bai-YT/MixedNUTS/resolve/main/cifar10_std_rn152.pt?download=true) |
+| CIFAR-10  | [Download](https://huggingface.co/Bai-YT/MixedNUTS/resolve/main/cifar10_std_rn152.pt?download=true)  |
 | CIFAR-100 | [Download](https://huggingface.co/Bai-YT/MixedNUTS/resolve/main/cifar100_std_rn152.pt?download=true) |
-| ImageNet | [Download](https://dl.fbaipublicfiles.com/convnext/convnextv2/im22k/convnextv2_large_22k_224_ema.pt) |
-
-For code and detailed usage, please refer to our [GitHub repository](https://github.com/Bai-YT/MixedNUTS).
+| ImageNet  | [Download](https://dl.fbaipublicfiles.com/convnext/convnextv2/im22k/convnextv2_large_22k_224_ema.pt) |
 
-<center>
-<img src=“main_figure.png” alt=“MixedNUTS Results” title=“Results” width=“800"/>
-</center>
+**For code and detailed usage, please refer to our [GitHub repository](https://github.com/Bai-YT/MixedNUTS).**
 
 
-#### Citing our work (BibTeX)
+## Citing our work (BibTeX)
 
 ```bibtex
 @article{MixedNUTS,
-title={MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers},
-author={Bai, Yatong and Zhou, Mo and Patel, Vishal M. and Sojoudi, Somayeh},
-journal={arXiv preprint arXiv:2402.02263},
-year={2024}
+  title={MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers},
+  author={Bai, Yatong and Zhou, Mo and Patel, Vishal M. and Sojoudi, Somayeh},
+  journal={Transactions on Machine Learning Research},
+  year={2024}
 }
 ```