hfkmt

google-research

Google Research

FluidX3D

The fastest and most memory efficient lattice Boltzmann CFD software, running on all GPUs via OpenCL. Free for non-commercial use.

evotorch

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

torchdynamo

A Python-level JIT compiler designed to make unmodified PyTorch programs faster.

Poisson_flow

Code for NeurIPS 2022 Paper, "Poisson Flow Generative Models" (PFGM)

Adan

Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

foldingdiff

Diffusion models of protein structure; trigonometry and attention are all you need!

GDN

Implementation code for the paper "Graph Neural Network-Based Anomaly Detection in Multivariate Time Series" (AAAI 2021)

fTetWild

Fast Tetrahedral Meshing in the Wild

mile

PyTorch code for the paper "Model-Based Imitation Learning for Urban Driving".

STEP

Code for our SIGKDD'22 paper Pre-training-Enhanced Spatial-Temporal Graph Neural Network For Multivariate Time Series Forecasting.

PhysCap_demo_release

PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time The implementation is based on [SIGGRAPH Aisa'20](https://vcai.mpi-inf.mpg.de/projects/PhysCap/).

uaamg

VectorAdam

VectorAdam for Rotation Equivariant Geometry Optimization

LanguageGroundedSemseg

Implementation for ECCV 2022 paper Language-Grounded Indoor 3D Semantic Segmentation in the Wild

GTA

Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT

gradientgating

Gradient gating (ICLR 2023)

PaGraph

SoCC'20 and TPDS'21: Scaling GNN Training on Large Graphs via Computation-aware Caching and Partitioning.

coronary-mesh-convolution

Implementation accompanying our STACOM (MICCAI) 2021 paper (https://doi.org/10.1007/978-3-030-93722-5_11)

of_pytorch_docker

Dockerfile to create an image with OpenFOAM-plus and PyTorch support

eman

Equivariant Mesh Attention Networks

amgnet

sdf-torch

Simple SDF mesh generation in Python

SPGRL

gnn_laminar_flow

Laminar flow prediction using graph neural networks

MGNNI

The implementation of MGNNI: Multiscale Graph Neural Networks with Implicit Layers (NeurIPS 2022)

citation-viewer

ffvc-mini

subprecision-cfd

Code for "Deep neural networks to correct sub-precision errors in CFD"