Powerful automatic differentiation in C++ and Python

[AAAI 2024] Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes

A header-only C++ library for numerical optimization --

Converts an input mesh to a signed distance field (SDF)

An efficient C++17 GPU numerical computing library with Python-like syntax

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO

Parallel algorithms and data structures for tree-based adaptive mesh refinement (AMR) with arbitrary element shapes.

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

An example of rendering grasses on terrain using draw DrawMeshInstancedIndirect and compute shader.

[AAAI 2024] Official PyTorch Implementation of ''BAT: Behavior-Aware Human-Like Trajectory Prediction for Autonomous Driving''.

Rhubarb Lip Sync is a command-line tool that automatically creates 2D mouth animation from voice recordings. You can use it for characters in computer games, in animated cartoons, or in any other p…

A GPU-parallel implementation of Marching Cubes in Vulkan

A nearly complete collection of prefix sum algorithms implemented in CUDA, D3D12, Unity and WGPU. Theoretically portable to all wave/warp/subgroup sizes.

Official Pytorch Implementation of SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis (CVPR 2024)

Official repository of "TexTile: A Differentiable Metric for Texture Tileability" [CVPR 2024]

Simple training pipeline for NN models required for motion matching in UE5.

A C++ library for image painting and editing workflows which make use of deep learning.

General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). Blazing fast, mobile-enabled, asynchronous and optimized for…

Easy to integrate Vulkan memory allocation library

Lightning fast C++/CUDA neural network framework

A code generator for array-based code on CPUs and GPUs

Exercise five for USC CSCI 599: Geometric Shape Modeling

Modified CUDA sample code to simulate a basic N-body problem for Janus Cosmological Model (JCM)

CUDA on non-NVIDIA GPUs

an implementation of parallel linear BVH (LBVH) on GPU

Gaia Physics Engine

SPHinXsys provides C++ APIs for engineering simulation and optimization. It aims at complex systems driven by fluid, structure, multi-body dynamics and beyond. The multi-physics library is based on…

Finite volume solver for incompressible multiphase flows with surface tension. Foaming flows in complex geometries.

2D and 3D physics engines focused on performance.