- [CoxKAN: Kolmogorov-Arnold Networks for Interpretable, High-Performance Survival Analysis](https://arxiv.org/abs/2409.04290) : CoxKAN is a novel framework for survival analysis based on Kolmogorov-Arnold Networks, which combines both interpretability and high performance. CoxKAN outperforms traditional models like the Cox proportional hazards model and rivals deep learning-based models, but with the advantage of interpretability, making it more useful in medical settings where understanding the underlying risk factors and relationships is essential. We find that CoxKAN extracts complex interactions between predictor variables and identifies the precise effect of important biomarkers on patient survival. | [code](https://github.com/knottwill/coxkan) ｜ 

- [RKAN: Residual Kolmogorov-Arnold Network](https://arxiv.org/abs/2410.05500) : Residual Kolmogorov-Arnold Network (RKAN) is designed to enhance the performance of classic CNNs by incorporating RKAN blocks into existing architectures. | [code](https://github.com/withray/residualKAN) 

- [Kolmogorov-Arnold Transformer](https://arxiv.org/abs/2409.10594) KAN was strong but faced scalability issues. KAT tackle this with 3 simple tricks. By combining KAN with Transformers, we've built a much stronger and more scalable model. | [code](https://github.com/Adamdad/kat) 

- [Kolmogorov-Arnold Fourier Networks](https://arxiv.org/abs/2502.06018) : This paper introduces Kolmogorov-Arnold Fourier Networks (KAF), a novel type of neural network that combines the Kolmogorov-Arnold representation theorem with Fourier series. KAF can be regarded as an extension of KAN, where the activation function is substituted with a combination of Fourier series and traditional activation functions. This paper evaluated the performance of simple CV, NLP, audio, and ML tasks on Kanbefair, and conducted experiments on various tasks such as ViT, GPT2, and PDE solving.Achieve good performance on most tasks.| [code](https://github.com/kolmogorovArnoldFourierNetwork/KAF) 

- [Effective Integration of KAN for Keyword Spotting](https://arxiv.org/abs/2409.08605)

- [Chebyshev Polynomial-Based Kolmogorov-Arnold Networks](https://arxiv.org/html/2405.07200)