To produce an embedding model that responds well to user provided instructions

The goal is to explore causal inference in time series and see if foundation models can help in the task.

Explore AI-assisted techniques to modernize Assembly programs into high-level language like C. Leverage recent advances in Large Language Models (LLMs) to generate human-readable, maintainable code from legacy systems. Evaluate how intermediate rep

Legal documentation processes are time-intensive, require specialized expertise, and are prone to human error, impacting efficiency and accuracy in handling complex agreements like MoUs, NDAs, and contracts.

Develop a solution that enables users to search and analyse food products, providing comprehensive insights into ingredient composition and health impact, including image-based analysis and personalized calorie tracking.

Farmers in Maharashtra face significant language barriers and have limited access to essential information regarding government schemes and agricultural best practices. Many farmers are not proficient in English, making it crucial to provide informat

The two primary requirements in the zero noise extrapolation (ZNE) protocol are the noise factors and the extrapolator. However, the same noise factors does not provide similar accuracy for circuits of different depth and width. And there is no obvio

IBM Quantum has been the leader in Quantum Technology in both hardware, middleware, and software. We have latest 156 qubits Heron processor chip which has capability to solve complex problems. Recently, several institutions has show-cased utility sca

Compute-intensive Monte Carlo methods are at the heart of material research. This project will explore specific software design patterns for heterogeneous computing specific to material research. The system of interest is dislocation loop models i