[ICLR2025] Kolmogorov-Arnold Transformer

ikan: many kan variants for every body

Simple, functional authorization library and role management for ruby

This is the implementation of the paper Enhanced Photovoltaic Power Forecasting: An iTransformer and LSTM-Based Model Integrating Temporal and Covariate Interactions

High order and sparse layers in pytorch. Lagrange Polynomial, Piecewise Lagrange Polynomial, Piecewise Discontinuous Lagrange Polynomial (Chebyshev nodes) and Fourier Series layers of arbitrary order. Piecewise implementations could be thought of as a 1d grid (for each neuron) where each grid element is Lagrange polynomial. Both full connected a…

Official implementation of "Quantum-inspired Kolmogorov-Arnold Network"

A systematic review of Kolmogorov-Arnold Networks that bridges them with MLPs, highlights their parameter-efficient, interpretable edge-basis design, maps the open-source ecosystem, and offers a practical guide to choosing architectures.

Example of replacing MLP with KAN in autoencoder(AE) and variational autoencoder(VAE)

Kolmogorov–Arnold Networks (KAN) in PyTorch

Implicit representation of various things using PyTorch and high order layers

KAE : KAN-based AutoEncoder (AE, VAE, VQ-VAE, RVQ, etc.)

GAN implemented with KAN convolution

Development of interactive platforms for city modeling and digital twins using React and MapLibre

Bottleneck KANConv for Unet

Experiments in language interpolation with high order sparse neural networks

Experiments on using Kolmogorov-Arnold Networks (KAN) on Graph Learning

Testing KAN-based text generation GPT models

Research project comparing Kolmogorov-Arnold Networks vs MLPs across chess engines, computer vision, and anomaly detection using Rust.

Neural Network Implicit Representation of Partial Differential Equations

Different projects to discover Data Science