Starred repositories
PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
A flexible neural net training library inspired by fast.ai
CUDA accelerated rasterization of gaussian splatting
Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Differentiable Finite Element Method with JAX
Source code for Fathony, Sahu, Willmott, & Kolter, "Multiplicative Filter Networks", ICLR 2021.
Lightweight, general, scalable C++ library for finite element methods
Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods
Diffusion models for image generation in Julia
Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"
APDL + MATLAB code for residual deformation calculations
High Order Hex-Quad Mesh (HOHQMesh) package to automatically generate all-quadrilateral meshes with high order boundary information.
[CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
Neural Network primitives with multiple backends
Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet
Neural Wavelet-domain Diffusion for 3D Shape Generation [SIGGRAPH Asia 2022]
Structure Preserving Machine Learning Models in Julia
Utility package for accessing common Machine Learning datasets in Julia
Kolmogorov-Arnold networks (KAN) as implicit functions (like NeRF but simpler)
