Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.

Repo for external large-scale work

SIMBA: SIngle-cell eMBedding Along with features

Open source code for AlphaFold 2.

Neural networks for cryo-EM reconstruction

A simple PyTorch implementation of BERT, complete with pretrained models and training scripts.

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning

Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it

Generate embeddings from large-scale graph-structured data.

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)

A Torch plugin for Unreal Engine 4.