Munachiso

S.A.M
Munachiso Samuel Nwadike
Google ScholargscholarTwittertwitter
Currently: Research Associate (III) with Dr. Kentaro Inui
Lab: MIMINT LabMI (Mechanistic Interpretability) @ MBZUAI
MSc in Machine Learning, MBZUAI
BSc in CS and Math, New York University
E: munachiso.nwadike@mbzuai.ac.ae (prior: msn307@nyu.edu)

Blog Post Link: Why Small Teams Still Work Big Magicrocket

Hi! I'm Sam, a passionate researcher building modern machine learning methods!

These days, I focus on mechanistic interpretability of large language models (LLMs), the core tech powering AI such as ChatGPT, Bard, Meta AI, and Grok.

I started my research career, much like the beginnings of a Bayesian Optimisation algorithm, excitedly and enthusiastically studying fairly different topics within AI. This allowed me to update my priors and build a good posterior distribution over the objective function of "contributing the best quality to the AI research community".

Along the way to optimising that objective, I've had the utmost honor & privilege of working, even more so excitedly and enthusiastically, on fundamental research topics, both at NYU and MBZUAI - the latter being a new and vibrant research institute led by Dr. Eric Xing (from Carnegie Mellon).

Welcome to have a look at my Google Scholar, and connect over email or Twitter (X) for collaborations!