Rohit K. Vartak

Durham, North Carolina

United States, 27705

I am a second-year M.S. in Computer Science student at Duke University.

My research interests lie in robustness and reasoning in LLMs. I am particularly interested in understanding how models reason, improving that reasoning process, and ensuring that these models remain efficient and scalable in real-world settings.

I am currently advised by Prof. Bhuwan Dhingra at Duke, where I am exploring the mathematical reasoning capabilities of multimodal LLMs.

Previously, I interned at CERT Labs, working under Prof. Praneeth Vepakomma at Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), where my focus was on improving the efficiency and scalability of large language models.

Additionally, I was advised by Prof. Monica Agrawal at Duke University, where I worked on studying and improving medical chatbots to enhance their accuracy and real-world usability.

Feel free to explore my work and reach out! 🚀

news

Jan 20, 2026	Excited to share that our work, “ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models”! has been accepted at ICLR 2026🚀
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-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models” is now on arXiv
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🚀

selected publications

ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models

Raghav Singhal^*, Kaustubh Ponkshe^*, Rohit Vartak^*, and 1 more author

arXiv preprint arXiv:2505.14238, 2025
PhysRev

Can Quantum-Mechanical Description of Physical Reality Be Considered Complete?

A. Einstein^*†, B. Podolsky^*, and N. Rosen^*

Phys. Rev., New Jersey. More Information can be found here , May 1935

Abs DOI HTML PDF Video

In a complete theory there is an element corresponding to each element of reality. A sufficient condition for the reality of a physical quantity is the possibility of predicting it with certainty, without disturbing the system. In quantum mechanics in the case of two physical quantities described by non-commuting operators, the knowledge of one precludes the knowledge of the other. Then either (1) the description of reality given by the wave function in quantum mechanics is not complete or (2) these two quantities cannot have simultaneous reality. Consideration of the problem of making predictions concerning a system on the basis of measurements made on another system that had previously interacted with it leads to the result that if (1) is false then (2) is also false. One is thus led to conclude that the description of reality as given by a wave function is not complete.