Hi! This is Aref Mahjoubfar. 👋

I'm currently working on:

Trustworthy AI

Uncertainty quantification utilizing token-level log-probabilities for sequences in a variety of tasks. Leveraging SHAP explanation models to calibrate LLM confidence scores. Rule-based (logically-grounded) actions in terms of confidence scores and explanations.

LLMs Confidence Score LOG-PROB SHAP PROLOG

My fascination with technology began in childhood, when I started designing custom websites from scratch. As I grew older, I explored application development with C#, further deepening my interest in software and automation.

During my medical education, I teamed up with a group of friends (EN.SAF 😘 — Fairness in Persian) to explore machine learning with a focus on computer vision in medical practice. This led to a thesis project that involved diagnosing Acute Lymphoblastic and Myeloblastic Leukemia (ALL and AML) through the analysis of blood and bone marrow slide images, with a dataset we collected over the span of one year. Over time, I honed my skills in Python 🐍 and worked extensively with machine learning libraries like PyTorch and TensorFlow. More recently, I've expanded into Natural Language Processing and working with Large Language Models, actively designing models to push the boundaries of Medical AI.

Life moves on, and I'm genuinely excited about the future and the next wave of technological innovations (This is what immortality is for 😉). I firmly believe in open science and the importance of combining our efforts, step by step, to lay the foundations for tomorrow's breakthroughs. This is how I can experience more in less time:)