Research
Building programming languages, tools, and software engineering techniques that make software more reliable, secure, and productive.
Large pre-trained language models such as GPT-3, Codex, and others can be tuned to generate code from natural language specifications of programmer intent. Such automated models have the potential to improve productivity for every programmer…
AI-driven test case generation for Visual Studio and VSCode This project aims at developing AI-based systems with the goal of automating software testing activities. We train large transformer models to learn from developers’ code how…
AI-driven code auto-completion in Visual Studio and VSCode The IntelliCode completions project started in 2018 when we tried to improve developer productivity through recommending class members based on user’s code context in Visual Studio. The…
Jigsaw Dataset: Natural language to Python Pandas code. Two datasets (PandasEval1 and PandasEval2) described in our paper, “Jigsaw: Large Language Models meet Program Synthesis”.
Microsoft Collective Communication Library (MSCCL) is a platform to execute custom collective communication algorithms for multiple accelerators supported by Microsoft Azure.
An efficient SMT solver Z3 is an efficient Satisfiability Modulo Theories (SMT) solver from Microsoft Research. Z3 is a solver for symbolic logic, a foundation for many software engineering tools. SMT solvers rely on a…