NextSegmPred reproduces the results obtained with the S2S (segmentation to segmentation) model described in the paper. Frames with no border correspond to the input while red borders indicate predicted frames.


The Global Climate Statistical Analysis Library (GCSAL) allows one to view climate statistics formulated from over 60 years of radiosonde data from weather balloons launched at more than 3000 locations around the world!

CLEVR Dataset Generator

This is the code used to generate the CLEVR dataset as described in the paper:  CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning. Presented at CVPR 2017


StarSpace is a general-purpose neural model for efficient learning of entity embeddings for solving a wide variety of problems.


ParlAI, is a unified platform, implemented in Python, for training and evaluating AI models on a variety of openly available dialog datasets using open-sourced learning agents.

Supervised-Hashing Baselines

This repository contains code to reproduce the baselines in How should we evaluate supervised hashing?


SparseConvNet implements spatially sparse convolutional networks.


This is a PyTorch implementation of the DrQA system.

Robocodes: Towards Generative Street Addresses from Satellite Imagery

This repo contains the code for creating generative street addresses from OSM input, as presented in our paper at the CVPR – EarthVision 2017


HVVR (Hierarchical Visibility for Virtual Reality) is an optimized software raycaster.


ELF is an Extensive, Lightweight and Flexible platform for game research, in particular for real-time strategy (RTS) games.


InferSent is a sentence embeddings method that provides semantic sentence representations.


SentEval is a library for evaluating the quality of sentence embeddings.

End-to-End Negotiator

This is a PyTorch implementation of research paper Deal or No Deal? End-to-End Learning for Negotiation Dialogues developed by Facebook AI Research.

Inferring and Executing Programs for Visual Reasoning (clevr-iep)

Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes. As a result, these black-box models often learn to exploit biases in the data rather than learning to perform visual reasoning.


Caffe2 is a machine learning framework enabling simple and flexible deep learning. Building on the original Caffe, Caffe2 is designed with expression, speed, and modularity in mind, and allows a more flexible way to organize computation.

Facebook AI Research Sequence-to-Sequence Toolkit

The FAIR Sequence-to-Sequence toolkit implements a fully convolutional model for text generation.


The CommAI project aims at developing new data-sets and algorithms to develop and evaluate general-purpose artificial agents that rely on a linguistic interface, and are capable of quickly adapting to a never-ending stream of tasks.


When you perform scientific experiments on remote servers, it can be a hassle to produce live visualizations of these experiments and to keep those visualizations organized. Visdom solves this problem for you!


Faiss is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM.