Teaching
University of Central Florida · Department of Computer Science
Current Topics in Machine Learning
Focus: Agentic AI
An advanced seminar covering the foundations and frontiers of agentic AI systems — including tool-using language models, planning under uncertainty, multi-agent coordination, and safety considerations for autonomous decision-making. Students engage with recent research papers and present on emerging topics each week.
Algorithms for Machine Learning
A foundational course covering core algorithmic ideas underlying modern machine learning — including optimization, supervised and unsupervised learning, neural networks, and model evaluation. Emphasis on both theoretical understanding and practical implementation.
Current Topics in Machine Learning
Focus: AI Alignment
A graduate seminar on the theory and practice of AI alignment — covering reinforcement learning from human feedback (RLHF), preference learning, reward modeling, constitutional AI, and inference-time safety methods. Weekly paper discussions drive the course, with students leading sessions on selected readings.
Teaching Philosophy
My teaching follows the Universal Design for Learning (UDL) framework, offering multiple means of engagement, representation, and assessment. I aim to make rigorous material accessible through diverse modalities — including weekly paper discussions, written assignments, quizzes, and student-led presentations.
At the graduate level, I treat courses as research incubators: students are expected to read primary literature critically, identify open problems, and connect theory to practice. At the undergraduate level, I emphasize building strong algorithmic intuition alongside the mathematical foundations needed for advanced study.