Google Research
Google Research
dads
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
recsim_ng
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
nested-transformer
Nested Hierarchical Transformer https://arxiv.org/pdf/2105.12723.pdf
recsim
A Configurable Recommender Systems Simulation Platform
electra
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the...
soft-dtw-divergences
An implementation of soft-DTW divergences.
hit-gan
Tensorflow implementation for "Improved Transformer for High-Resolution GANs" (NeurIPS 2021).
reverse-engineering-neural-networks
A collection of tools for reverse engineering neural networks.
arco-era5
Recipes for reproducing Analysis-Ready & Cloud Optimized (ARCO) ERA5 datasets.