About me
I am a PhD student in the Language, Computation, and Cognition Lab led by Prof. Dr. Michael Hahn. I try to use and develop formal methods to enhance our understanding of modern LLMs.
Research Interests
My research interests mainly lies in trying to understand the capabilities and limitations of architectures powering the most powerful AI models of today – Transformers and State Space Models. My goal is to address core questions such as:
- Which tasks are these architectures inherently incapable of performing, regardless of how much we scale them up?
- How can we engineer our way around these limitations to build more robust and scalable architectures?
- Can we develop a theoretically sound framework that actually predicts the in-context learning abilities a large-scale model might develop?
Academic and Professional Background
I also did my Masters in the Language Science and Technology department at Saarland University, Germany and have then continued on to do my PhD here. Before that, I completed my undergraduate degree in Computer Science at Manipal Institute of Technology in 2020. Following that, I spent three years working as a Machine Learning Engineer in the R&D team at Glib.ai. I have also had internships at Samsung R&D, Bangalore in their On-Device AI division and at Novartis, Hyderabad, India.
Beyond work
When I’m not buried deep into understanding some research paper or am not scratching my head debugging my code, I indulge my interests to keep myself balanced (or at least that’s what I think). I am semi-decent at dancing, enjoy playing chess, and love experimenting with cooking. I am always up for hiking and find the most joy in discussing about philosophical questions and ethical dilemmas. Having these conversations on a hike would be chef’s kiss xD.
Thank you for visiting my page! If you’re interested in my work, would like to collaborate or just chat in general, feel free to reach out !