Research Tools: code, datasets, & models

FreeLB is an adversarial training approach for improving transformer-based language models on Natural Language Understanding tasks. It accumulates the gradient in the ascent steps and updates the parameters with the accumulated gradients, which is approximately…

Prevalent: A Pretrained Generic VLN Agent [Code Clean Is In Progress] This repository contains source code to reproduce the results presented in the paper: Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training, CVPR…

This repository contains source code to reproduce the results presented in the paper: Feature Quantization Improves GAN Training, 2020 Yang Zhao, Chunyuan Li, Ping Yu, Jianfeng Gao, Changyou Chen (opens in new tab)

Optimus: the first large-scale pre-trained VAE language model

The Microsoft Rocketbox Avatar library consists of 115 characters and avatars fully rigged and with high definition that was developed over the course of 10 years. The diversity of the characters and the quality of…

Coyote is a programming framework for building reliable asynchronous software. Coyote ensures design and code remain in sync, dramatically simplifying the addition of new features. Coyote comes with with a systematic testing engine that allows…

The RoomAlive Toolkit is an open source SDK that enables developers to calibrate a network of multiple Kinect sensors and video projectors. The toolkit also provides a simple projection mapping sample that can be used…

Reference implementation and test synthetic data for “Sorted Center Time” echo density measure for acoustic impulse responses

This repository provides a code base to evaluate and train models from the paper “Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representations”.

Kuku is a simple open-source (MIT licensed (opens in new tab)) cuckoo hashing library developed by the Cryptography and Privacy Research group at Microsoft. Kuku is written in modern standard C++ and has no external…