Yogesh Kulkarni

I am a first-year Computer Science Ph.D. student at the School of Computing and Augmented Intelligence (SCAI), Arizona State University, advised by Dr. Pooyan Fazli and part of the People and Robots Laboratory (PeRL). My research revolves around extending Large Vision Language Models (LVLMS) for Video Understanding and aligning with human preferences using Reinforcement Learning.

Previously, I graduated from the University of Southern California (USC) with a Master’s in Computer Science. At USC, I was a Graduate Research Assistant at the USC Institute for Creative Technologies (ICT), where I worked with 3D Point Clouds, particularly at the intersection of GANs, Diffusion Models, and Gaussian Splatting for style transfer in the 3D domain. In Summer 2023, I had the privilege to intern at Nokia Bell Labs, contributing to efficient geo-distributed LLM training across heterogeneous clusters.

Before coming to the US, I graduated from the Pune Institute of Computer Technology with a Bachelor’s in Computer Engineering. During those four years, my passion for Machine Learning led me to a variety of impactful projects and research endeavors. At Episource LLC, I developed a real-time Clinical Text Abbreviation Disambiguation solution and enhanced the company’s Named Entity Recognition (NER) model by mapping over 200 clinical drugs. My research at RBCDSAI (IIT Madras) involved building an End-to-End framework for detecting Electricity Theft in Industrial Smart Grids, and at DRDO HQ, I devised a robust framework for malware analysis of images.

I was born and raised in New Delhi, where I spent 14 years at Mount Carmel School. My journey took me from Pune for my undergraduate studies, to Los Angeles for my Master’s, a summer in New York City, and now to Tempe, Arizona. Life has a way of taking us on unexpected journeys, and I’ve learned to follow where it leads.

“Sometimes the best journeys in life are the ones we never expected to take.” ~ Unknown