Update README.md

README.md

@@ -34,6 +34,7 @@ A curated list of awesome libraries, projects, tutorials, papers, and other reso
 ## Papers
 
 - [KAN: Kolmogorov-Arnold Networks](https://arxiv.org/abs/2404.19756) : Inspired by the Kolmogorov-Arnold representation theorem, we propose Kolmogorov-Arnold Networks (KANs) as promising alternatives to Multi-Layer Perceptrons (MLPs). While MLPs have fixed activation functions on nodes ("neurons"), KANs have learnable activation functions on edges ("weights"). KANs have no linear weights at all -- every weight parameter is replaced by a univariate function parametrized as a spline. We show that this seemingly simple change makes KANs outperform MLPs in terms of accuracy and interpretability. For accuracy, much smaller KANs can achieve comparable or better accuracy than much larger MLPs in data fitting and PDE solving. Theoretically and empirically, KANs possess faster neural scaling laws than MLPs. For interpretability, KANs can be intuitively visualized and can easily interact with human users. Through two examples in mathematics and physics, KANs are shown to be useful collaborators helping scientists (re)discover mathematical and physical laws. In summary, KANs are promising alternatives for MLPs, opening opportunities for further improving today's deep learning models which rely heavily on MLPs.
+- [KAN 2.0: Kolmogorov-Arnold Networks Meet Science](https://arxiv.org/abs/2408.10205)
 - [KAN or MLP: A Fairer Comparison](https://arxiv.org/abs/2407.16674) : Under the same number of parameters or FLOPs, we find KAN  outperforms MLP only in symbolic formula representing, but remains inferior to MLP on other tasks of machine learning, computer vision, NLP, and audio processing. We also conduct ablation studies on KAN and find that its advantage in symbolic formula representation mainly stems from its B-spline activation function. | [code](https://github.com/yu-rp/KANbeFair) ｜ ![Github stars](https://img.shields.io/github/stars/yu-rp/kanbefair.svg)
 - [DropKAN: Regularizing KANs by masking post-activations](https://arxiv.org/abs/2407.13044) : DropKAN (Dropout Kolmogorov-Arnold Networks) is a regularization method that prevents co-adaptation of activation function weights in Kolmogorov-Arnold Networks (KANs). DropKAN operates by randomly masking some of the post-activations within the KANs computation graph, while scaling-up the retained post-activations. We show that this simple procedure that require minimal coding effort has a regularizing effect and consistently lead to better generalization of KANs. | [code](https://github.com/Ghaith81/dropkan) ｜ ![Github stars](https://img.shields.io/github/stars/Ghaith81/dropkan.svg)
 - [Rethinking the Function of Neurons in KANs](https://arxiv.org/abs/2407.20667) : The neurons of Kolmogorov-Arnold Networks (KANs) perform a simple summation motivated by the Kolmogorov-Arnold representation theorem, Our findings indicate that substituting the sum with the average function in KAN neurons results in significant performance enhancements compared to traditional KANs. Our study demonstrates that this minor modification contributes to the stability of training by confining the input to the spline within the effective range of the activation function. | [code](https://github.com/Ghaith81/dropkan) ｜ ![Github stars](https://img.shields.io/github/stars/Ghaith81/dropkan.svg)