i’m currently pursuing my Master’s in Computer Science at UMass Amherst.
lately, I’ve been fascinated by how small language models reason — how we can help them think more reliably, and how fine-tuning them on ontologically diverse data and how we might make them better at understanding complex, domain-specific questions, especially in Medical QA.
i’ve been trying to get back into writing more regularly — sharing notes, ideas, and half-formed thoughts as I explore new papers and projects. Feel free to check out my writing at blog.
12/12/25 Update
A recent thing that I have been interested in recent times is how Tiny Self Impoving Reasoning Models work. Currently reading through the following:


