Hi, I'm Arnav — a curious undergrad who likes taking models apart to see why they work. Outside research I read widely and consume unhealthy amounts of media.
Currently
NowStudying the internals of MLLMS.Building toward a larger aim: efficient and reliable vision-language models and agents.
NextEfficient & reliable VLM agents.Where I want to take my research.
Open toResearch internships & collaborations.
About
Writing
Dec 2025The problem of determinismIf we lived in a world where an algorithm could predict the result of our every decision.