The MIT Language Modeling (MITLM) toolkit is a set of tools designed for the efficient estimation of statistical n-gram language models involving iterative parameter estimation.  It achieves much of its efficiency through the use of a compact vector representation of n-grams.  Details of the data structure and associated algorithms can be found in the following paper: Bo-June (Paul) Hsu and James Glass.

The Virtual Glass software lets anyone, with any or no glass experience, design and visualize glass cane, and to get a sense of what that cane will look like on a blown piece, all on your computer (without lifting a pipe!). The goal is to allow the exploration of cane designs, especially new cane designs, and settle on a nice-looking design before going through the effort of making it.

KPart is a tool for partitioning the last-level cache (LLC) dynamically between co-running applications on an Intel multicore processor with way-partitioning support. KPart is designed to sidestep a key limitation of way-partitioning: coarse-grained partition sizes.

Julia is a high-level, high-performance dynamic programming language for numerical computing.

This repository contains the authors' implementation from "Data Augmentation using Learned Transformations for One-shot Medical Image Segmentation", which will be presented as an oral at CVPR 2019. We provide code for training spatial and appearance transform models, and for using the transform models to synthesize training examples for segmentation.

Coauthor is a tool for group collaboration, discussion, keeping track of notes/results of meetings, etc. Its primary goal is to ease multiauthor collaboration on unsolved problems in theoretical computer science, so e.g. you'll find LaTeX math support; hopefully it will have applications in other fields too.

We present Carnelian, a pipeline for alignment-free functional binning and abundance estimation, that leverages low-density even-coverage locality sensititve hashing to represent metagenomic reads in a low-dimensional manifold. When coupled with one-against-all classifiers, our tool bins whole metagenomic sequencing reads by molecular function encoded in their gene content at significantly higher accuracy than existing methods, especially for novel proteins.

A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents

We’re releasing a Neural MMO, a massively multiagent game environment for reinforcement learning agents. Our platform supports a large, variable number of agents within a persistent and open-ended task. The inclusion of many agents and species leads to better exploration, divergent niche formation, and greater overall competence.

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

This is a pytorch based implementation for our paper on learning to control self-assembling agents using deep reinforcement learning.