Rohit K. Vartak
Duke University | Not a slightest clue in life
I am a second-year M.S. student in Computer Science at Duke University.
I am currently part of CERT Labs, working under Prof. Praneeth Vepakomma at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where my focus is on reducing the memory utilization of large language models (LLMs).
Additionally, I am advised by Prof. Monica Agrawal at Duke University, where I work on studying and improving medical chatbots to enhance their accuracy and real-world usability.
Still figuring out what truly excites me, but I’ll probably update this when I do! 🫠
Feel free to explore my work and reach out! 🚀
news
| Jun 26, 2025 | Excited to share our latest work, ““What’s Up, Doc?”: Analyzing How Users Seek Health Information in Large-Scale Conversational AI Datasets”! Now available on arXiv🚀 |
|---|---|
| May 21, 2025 | 🚀 Just dropped: “ABBA: Highly Expressive Hadamard Product Adaptation for LLMs” is now on arXiv 📌 TLDR here |
| Mar 13, 2025 | Excited to share our latest work, “Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning”! Now available on arXiv🚀 |
| May 15, 2024 | Accepted for Masters of Science in CS at Duke University |
| Jul 26, 2022 | Selected for IDDDP from Electrical Engineering to C-MInDS (AI/ML) at IIT Bombay |
latest posts
| Jul 25, 2025 | LoFT - Low-Rank Adaptation That Behaves Like Full Fine-Tuning |
|---|---|
| Nov 11, 2024 | Introduction to Diffusion Models |
| Jul 12, 2023 | a post with bibliography |