PhD Student · Reinforcement Learning & Maths Reasoning · UMBC
PhD student in Computer Science at UMBC specializing in Machine Learning, Reinforcement Learning, and Mathematical Reasoning in LLMs. My research focuses on enhancing reasoning in LLMs, improving RL sample efficiency, and developing Sim2Real frameworks — with publications at NeurIPS, AAAI, and RSS.
Research Interests
Enhancing math reasoning capabilities in large language models using RLHF and schema-based instruction.
Deep RL, hierarchical agents, Sim2Real transfer, graph attention in R-GCN frameworks, sample efficiency.
YOLO-based object detection, autonomous drone navigation, real-world RL deployment.
Recent Highlights
Featured Projects
An AI agent that fetches recent ArXiv research papers based on search — like Google Scholar but more user-friendly and readable.
ML model to detect whether an essay was written by a student or an LLM. Finished in the top 25% of the Kaggle leaderboard.
Python package fetching real-time International Space Station data. Over 60,000 downloads on PyPI.
Self-driving prototype using CNNs and OpenCV to predict steering angles from dash-cam image inputs.