M.S. Computer Science · The George Washington University
I am a Master's student in Computer Science at The George Washington University (GPA: 4.0). My academic research focuses on Large Language Models (LLMs), with a strong emphasis on model alignment, trustworthy AI, and behavioral evaluation. My recent work investigates reliability failure modes, such as persona-induced information asymmetry, to better understand the trade-offs between sycophancy and factual integrity. I am actively seeking Ph.D. opportunities for Fall 2027 to further advance research in AI safety and information equity.
Lead Researcher · Formulated a novel reliability failure mode in frontier models. Developed an evaluation benchmark of 1,800+ ground-truth checklists and proposed quantitative metrics (FC, IOS, PTG) to analyze the "Sycophancy-Completeness Trade-off."
Research Project · Architected a federated learning framework implementing Parameter-Efficient Fine-Tuning (PEFT) strategies to maximize internal model coherence for LLM alignment in decentralized, resource-constrained environments.
Co-Author · Developed a training-free adaptive 360-degree video streaming framework utilizing semantic potential fields for zero-shot adaptation. Conducted 3,600+ large-scale simulations demonstrating competitive QoE and low latency.