Research Tools: code, datasets, & models

This repo provides code for generating the sepsis cohort from MIMIC III dataset. Our main goal is to facilitate reproducibility of results in the literature.

Unsupervised Domain Adaptation algorithms robust to mismatched label distributions

Accompanying paper: iPhys: An Open Non-Contact Imaging-Based Physiological Measurement Toolbox A MATLAB toolbox for iPPG analysis. The toolbox includes implementations of commonly used methods.

Accompanies the paper Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)

A collection of chess engines that play like humans, from ELO 1100 to 1900.

Code for replication of experiments in the paper: Minimax Estimation of Conditional Moment Models Nishanth Dikkala, Greg Lewis, Lester Mackey, and Vasilis Syrgkanis arXiv preprint arXiv:2006.07201 (2020)

MoveBox is a toolbox to animate the Microsoft Rocketbox avatars using motion captured (MoCap). Motion capture is performed using a single depth sensor, such as Azure Kinect or Windows Kinect V2. Our toolbox enables real-time…

Search4Code is a large-scale web query based dataset of code search queries for C# and Java. The Search4Code data is mined from Microsoft Bing’s anonymized search query logs using weak supervision technique.

Uncertainty-aware self-training (UST) for few-shot text classification with pre-trained language models. With only 20-30 labeled samples per class for each task, UST can perform similar to fully supervised pre-trained language models like BERT fine-tuned on…

This self-hosted service developed for Azure, including its orchestration engine and security tools (including MSR’s RESTler), enables developers to embed security tooling into their CI/CD workflows.