Researcher tools: code, datasets, & models
An index of datasets, SDKs, APIs and other open source code created by Microsoft researchers and shared with the broader academic community. We also maintain a collection highlighting some of the tools you’ll find here.
Dataset Source Code
MarS
MarS is a cutting-edge financial market simulation engine powered by the Large Market Model (LMM), a generative foundation model.
Dataset Source Code
TamGen
This is the implementation of the paper “TamGen: Target-aware Molecule Generation for Drug Design Using a Chemical Language Model”.
Download
RAD-DINO model
RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method DINOv2. RAD-DINO is described in detail in RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision (F. Pérez-GarcÃa, H. Sharma, S.…
Download
MAIRA-2 model
MAIRA-2 is a multimodal transformer designed for the generation of grounded or non-grounded radiology reports from chest X-rays. It is described in more detail in MAIRA-2: Grounded Radiology Report Generation (S. Bannur, K. Bouzid et al.,…
Dataset Source Code
RadFact: An LLM-based Evaluation Metric for AI-generated Radiology Reporting
RadFact is a framework for the evaluation of model-generated radiology reports given a ground-truth report, with or without grounding. Leveraging the logical inference capabilities of large language models, RadFact is not a single number but a suite of…
Dataset Source Code
TerraTrace: Spatio-Temporal Signatures for Land Use Analytics
Understanding land use over time is critical to tracking events related to climate change, like deforestation. However, satellite-based remote sensing tools which are used for monitoring struggle to differentiate vegetation types in farms and orchards…
Dataset Source Code
OmniParser
OmniParser is a comprehensive method for parsing user interface screenshots into structured and easy-to-understand elements, which significantly enhances the ability of GPT-4V to generate actions that can be accurately grounded in the corresponding regions of…
Download
FStar Data Set v2
This dataset is the Version 2.0 of the FStar Data Set. This dataset’s primary objective is to train and evaluate Proof-oriented Programming with AI (PoPAI, in short). Given a specification of a program and proof…
Download
FStar Data Set v1
This dataset contains programs and proofs in F* proof-oriented programming language. The data, proposed in Towards Neural Synthesis for SMT-Assisted Proof-Oriented Programming, is an archive of source code, build artifacts, and metadata assembled from eight…