About
I am the Technical Lead at RELAI, where I lead the development and deployment of our AI solutions.
In 2024, I completed my PhD in the Department of Electrical and Computer Engineering at the University of Maryland, College Park, where I worked with Prof. Soheil Feizi.
My research interests are in reliability of AI models and systems (including LLMs, AI agents). I love working on generalized algorithms that can solve a wide variety of problems.
Here's my Google Scholar profile and here's my CV.
Timeline
Technical Lead at RELAI
PhD in Electrical and Computer Engineering, University of Maryland, College Park
M.Tech in Electrical Engineering, IIT Madras
For my Master's thesis, I worked on image denoising with Prof. A. N. Rajagopalan. In the summer of 2019, I did an internship with KLA where I worked on super-resolution of SEM images.
Co-Founder, Tessact
At Tessact, our mission was to bring the latest advancements in Deep Learning to the media industry. Specifically, we developed software for scalable and accurate frame-by-frame video annotation. This is the first and, arguably, the hardest step in automating the process of serving contextual advertisements and meeting compliance standards.
B.Tech in Electrical Engineering, IIT Bombay
Here, I had my first exposure to the wonderful world of Computer Vision, in the courses taught by Prof. Ajit Rajwade.
Publications
-
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative ModelsInternational Conference on Learning Representations (ICLR), 2025
-
On mechanistic knowledge localization in text-to-image generative modelsForty-first International Conference on Machine Learning (ICML), 2024
-
Fast Adversarial Attacks on Language Models In One GPU MinuteInternational Conference on Learning Representations (ICLR), 2024
-
LLM-Check: Investigating Detection of Hallucinations in Large Language ModelsAdvances in Neural Information Processing Systems (NeurIPS), 2024
-
FOCUS: Familiar Objects in Common and Uncommon SettingsProceedings of the 39th International Conference on Machine Learning, 2022
-
Unpaired Image DenoisingIEEE International Conference on Image Processing (ICIP), UAE (Virtual), October 2020
Preprints
-
Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models
-
Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
-
Invariant Learning via Diffusion Dreamed Distribution Shifts
Accomplishments
-
Outstanding Graduate Student Award December 2023The award conveys the honor of being recognized as among the top 2% of campus Graduate Assistants at the University of Maryland in a given year.
-
Siemens Prize September 2020Awarded to the M. Tech student with the best academic record in Electrical Engineering at IIT Madras.
-
Prof. M K Achuthan Prize April 2020Awarded to the M. Tech student with the best academic record in the first year in Electrical Engineering at IIT Madras.
-
All India Rank 80 in IIT-JEEJune 2012Secured 80th rank (~ 470 000 total candidates, 99.98th percentile) in the Joint Entrance Examination conducted by the IITs in 2012.
Teaching
I have been a teaching assistant for the following courses:
University of Maryland, College Park
- ENEE324: Engineering Probability Fall 2021
- ENEE440: Microprocessors Spring 2021
IIT Madras
- EE5175: Image Signal Processing Spring 2020
- EE6133: Multirate Digital Signal Processing Fall 2019
- EE3110: Probability Foundations for Electrical Engineers Spring 2019
Outside of Work...
I am into badminton and Dota 2. I am also an amateur photographer (check out my Instagram) and web developer; this website is a showcase of my budding skills.
Although it's hard for me to find the time these days, I enjoy watching sci-fi/fantasy movies, TV shows.