the human behind the models 🦦

My favorite projects all start the same way: “I wonder if…” Sometimes it’s a question about how a model learns. Sometimes it’s whether an LLM can solve a problem it probably shouldn’t. Occasionally it’s because I saw a paper at 2 a.m. and thought, “That can’t be that hard.” It usually is.

I’m fascinated by Machine Learning, Deep Learning, Reinforcement Learning, Robotics, Computer Vision, Natural Language Processing, Large Language Models, Generative AI, Agentic AI, Multimodal AI, Causal Inference, High-Performance Machine Learning, Explainable AI, and Trustworthy AI. I love exploring how these ideas connect and, more importantly, how they can be used to solve problems that matter.

Before Columbia, I studied Computer Science with a specialization in Data Science at VIT and spent a couple of years as a software engineer. While I enjoyed building software, I realized the part I loved most wasn’t just shipping features—it was understanding why things worked, why they failed, and whether there was a better way to solve the problem.

That curiosity has become a bit of a personality trait. I have a habit of collecting side projects, opening far too many research papers at once, and accidentally turning weekend ideas into month-long adventures. My GitHub is full of experiments that began with “I’ll just try something quickly.”

This website is where all of those adventures live. It’s part portfolio, part technical notebook, part blog, and part playground where I experiment with design, AI, and web technologies. If something catches my interest, chances are it’ll eventually find its way here—whether that’s a research project, a deep dive, a visualization, or an unnecessarily over-engineered feature.