danielzuegner/code-transformer
Implementation of the paper "Language-agnostic representation learning of source code from structure and context".
Senior researcher at Microsoft Research. Past: PhD student at TU Munich
Implementation of the paper "Language-agnostic representation learning of source code from structure and context".
Implementation of the paper "Certifiable Robustness and Robust Training for Graph Convolutional Networks".
Implementation of the paper "Adversarial Attacks on Neural Networks for Graph Data".
Torch-native, batchable, atomistic simulations.
Implementation of the paper "Adversarial Attacks on Graph Neural Networks via Meta Learning".
Implementation of the paper "NetGAN: Generating Graphs via Random Walks".
Controlling a Roomba with a PS4 controller and playing songs
Python Materials Genomics (pymatgen) is a robust materials analysis code that defines classes for structures and molecules with support for many electronic structure codes. It powers the Materials Project.
Official implementation of MatterGen -- a generative model for inorganic materials design across the periodic table that can be fine-tuned to steer the generation towards a wide range of property constraints.
atomate2 is a library of computational materials science workflows
Graph Neural Network Library for PyTorch
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Pure-python library for adding annotations to PDFs
Implementation code for the paper "Graph Neural Network-Based Anomaly Detection in Multivariate Time Series"
Discrete Graph Structure Learning for Forecasting Multiple Time Series, ICLR 2021.
An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]
Python scripts for MacOS (OS X) that create, manipulate, and query PDF files