Projects
Our goal is to provide a simple and easy way to (i) remotely measure and observe the health of a sensor, and (ii) empower users to specify their acceptable data quality threshold driven by the application requirements.
Established:
Established:
We are designing programming languages for building safe and reliable asynchronous systems. These languages are based on the programming idiom of asynchronous communicating state machines. They offer first-class support for writing safety and liveness specifications as well as building abstract models…
Established:
Corral is a whole-program analysis tool for Boogie programs. Corral uses goal-directed symbolic search techniques to find assertion violations. It leverages the powerful theorem prover Z3. It is available open source on GitHub. Corral, by default, does a bounded search up to a recursion depth…
Established:
The goal of the Physical Analytics project, or Phytics, is to perform analytics on the physical actions of users. Such analytics would be valuable in a variety of contexts where the design of a physical space is intertwined with how…
Established:
Towards efficient AI/ML deployment The AI Infrastructure team at Microsoft Research India works on cutting-edge systems optimizations for improving the efficiency of a variety of AI/ML workloads, including an emerging class of workloads, namely, serving large language models (LLMs). AI/ML models…
At Microsoft Research Lab India, we conduct a variety of healthcare related research, including smartphone-based low-cost diagnostics, generative AI chatbots to support the healthcare ecosystem, and promote mental well-being of employees.
Algorithm to generate complex LLM prompts from scratch Given a task in the form of a basic description and its training examples, prompt optimization is the problem of synthesizing the given information into a text prompt for a large language…
Design, analysis and interpretability of large language models Transformers and large language models (LLMs) have had enormous success in recent years. Yet they remain poorly understood, in particular why and how they work. We are trying to answer such questions…