Dataset Source Code
ProtNote: a multimodal method for protein-function annotation
ProtNote is a multimodal deep learning model that leverages free-form text to enable both supervised and zero-shot protein function prediction.
Researcher tools: code, datasets, & models
Discover an index of datasets, SDKs, APIs and open-source tools developed by Microsoft researchers and shared with the global academic community below. These experimental technologies—available through Azure AI Foundry Labs (opens in new tab)—offer a glimpse into the future of AI innovation.
Dataset Source Code
AutoVerus
Automatically synthesize proof annotations that help Verus prove the correctness of Rust code.
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…
Dataset Source Code
Privacy-preserving in-context learning with differentially private few-shot generation
This is a codebase to perform privacy-preserving in-context learning with differentially private few-shot generation.
Dataset Source Code
Eureka ML Insights
This repository contains the code for the Eureka ML Insights, a framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings. The framework is designed to help researchers and practitioners run reproducible evaluations…
Dataset Source Code
Data Formulator
Transform data and create rich visualizations iteratively with AI.
Dataset Source Code
rStar
A self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superior models. rStar decouples reasoning into a self-play mutual generation-discrimination process.
Dataset Source Code
VPTQ
Vector Post-Training Quantization (VPTQ) is a novel Post-Training Quantization method that leverages Vector Quantization to high accuracy on LLMs at an extremely low bit-width (
Dataset Source Code
EASIER: Efficient Auto-scalable Scientific Infrastructure for Engineers and Researchers
EASIER is a domain specific language embedded in PyTorch to automatically scale physical simulations up and out. It just-in-time (JIT) distributes tensor dataflows that describe physical simulations to any number of workers and compiles them…