Current project's

Project - TSFM for causal inference in time series

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

  • In progress

Project - Enhancement of Torch.Compile Workflow with Observability Hooks

Integration of profiling into torch.compile workflow with inductor backend, by identifying the following: 1. Which metrics to collect - timing, register access counters, etc 2. Where to insert hooks - Fx graph, Inductor IR, Triton IR, etc 3. Areas

  • In progress

Project - TSFM Notebooks

Build notebooks to increase open-source adoption of TSFM models

  • In progress

Project - Coach-Crew Service: Multi-Agent Self-Evaluation Framework Using AI Coa

1. To build an AI-driven evaluation system where AI agents assess and improve the performance of other AI agents. 2. To implement a multi-layer coaching pipeline (Primary Generator → Lightweight Coach → Heavy Coach) for scalable, reliable, self-eval

  • In progress

Project - Instruction Following Dense Passage Retrieval

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

  • In progress

Project - Assembly to C Translation using LLMs

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

  • In progress

Project - Adaptive Graph Topologies for Multi-Agent Systems

This project proposes the development of AdaptiveGraphMAS, a reinforcement learning-driven framework for autonomous construction and optimization of multi-agent system (MAS) topologies. Inspired by the MasHost paradigm, this research aims to advance

  • In progress

Project - Time Series Foundation Models

Build Newer architectures, benchmarks, and leaderboards in the area of Time-Series Foundation Models. Publish the work in top-tier conferences.

  • In progress

Project - LLM-Decoder for SNMP Traps and Syslogs

Project Overview Network operation teams often face thousands of cryptic traps and syslogs per day. This Watsonx.ai-based solution will use LLMs enhanced with Retrieval-Augmented Generation (RAG) to translate raw logs into plain English, classify th

  • In progress

How it Work

Mentor and Student do the registration

Menter create the project and student applies on it.

Student Upload the Terms & Conditions and Mentor approves it

Mentor Reviews the Required document uploaded by student

Student submits the project