quiqi / relu_kan
☆72Updated 3 months ago
Related projects: ⓘ
- Benchmark for efficiency in memory and time of different KAN implementations.☆104Updated 3 weeks ago
- Kolmogorov-Arnold Networks (KAN) using Jacobi polynomials instead of B-splines.☆28Updated 4 months ago
- Kolmogorov–Arnold Networks with modified activation (using fully connected network to represent the activation)☆98Updated 4 months ago
- Kolmogorov-Arnold Networks (KAN) using orthogonal polynomials instead of B-splines.☆23Updated 4 months ago
- C++ and Cuda ops for fused FourierKAN☆71Updated 4 months ago
- An easy to use PyTorch implementation of the Kolmogorov Arnold Network and a few novel variations☆147Updated last month
- Benchmarking and Testing FastKAN☆57Updated 3 months ago
- A modified CNN architecture using Kolmogorov-Arnold Networks☆59Updated 3 months ago
- The codes to replicate the simulation of the paper :"Wav-KAN: Wavelet Kolmogorov-Arnold Networks"☆88Updated 3 months ago
- ☆111Updated 4 months ago
- The official repository for HyperZ⋅Z⋅W Operator Connects Slow-Fast Networks for Full Context Interaction.☆29Updated this week
- This code implements a Radial Basis Function (RBF) based Kolmogorov-Arnold Network (KAN) for function approximation.☆24Updated 3 months ago
- FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)☆332Updated 2 months ago
- A More Fair and Comprehensive Comparison between KAN and MLP☆122Updated last month
- This repository contains a better implementation of Kolmogorov-Arnold networks☆59Updated 4 months ago
- Kolmogorov-Arnold Networks with various basis functions like B-Splines, Fourier, Chebyshev, Wavelets etc☆30Updated 4 months ago
- Implementation of MambaFormer in Pytorch ++ Zeta from the paper: "Can Mamba Learn How to Learn? A Comparative Study on In-Context Learnin…☆20Updated last week
- ☆32Updated 4 months ago
- Convolutional layer for Kolmogorov-Arnold Network (KAN)☆75Updated 3 months ago
- ☆30Updated 4 months ago
- ☆15Updated this week
- Training small GPT-2 style models using Kolmogorov-Arnold networks.☆105Updated 3 months ago
- Implementation of xLSTM in Pytorch from the paper: "xLSTM: Extended Long Short-Term Memory"☆90Updated last week
- Trying out the Mamba architecture on small examples (cifar-10, shakespeare char level etc.)☆40Updated 9 months ago
- High order and sparse layers in pytorch. Lagrange Polynomial, Piecewise Lagrange Polynomial, Piecewise Discontinuous Lagrange Polynomial…☆40Updated 2 months ago
- Implementation of Griffin from the paper: "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"☆48Updated last week
- Evaluating the Mamba architecture on the Othello game☆41Updated 4 months ago
- A Triton Kernel for incorporating Bi-Directionality in Mamba2☆43Updated last week
- A single repo with all scripts and utils to train / fine-tune the Mamba model with or without FIM☆46Updated 5 months ago
- Kolmogorov-Arnold Networks (KAN) using Chebyshev polynomials instead of B-splines.☆336Updated 4 months ago