- [AF-KAN: Activation Function-Based Kolmogorov-Arnold Networks for Efficient Representation Learning](https://arxiv.org/abs/2503.06112) | [code](https://github.com/hoangthangta/All-KAN) |  - expand ReLU-KAN with various activations and their function combinations

- [MatrixKAN: Parallelized Kolmogorov-Arnold Network](https://arxiv.org/abs/2502.07176) : MatrixKAN is a novel KAN optimization that parallelizes B-spline calculations with matrix representation and operations, thus significantly improving effective computation time for models utilizing high-degree B-splines. This paper demonstrates the superior scaling of MatrixKAN's computation time relative to B-spline degree and speedups of approximately 40x relative to KAN, with significant additional speedup potential for larger datasets or higher spline degrees. | [code](https://github.com/OSU-STARLAB/MatrixKAN) | 

- [CVKAN: Complex-Valued Kolmogorov-Arnold Networks](https://arxiv.org/abs/2502.02417) | [code](https://github.com/M-Wolff/CVKAN) |  - Transferred KANs into the complex-valued domain using Radial Basis Functions and added tools for improved Plotting and Interpretability

- 1957-[On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables](https://cs.uwaterloo.ca/~y328yu/classics/Kolmogorov57.pdf) : The original Kolmogorov Arnold paper