Hugh Flournoy Van Deventer V
I am a senior at the University of Michigan double majoring in Mathematics and Interdisciplinary Physics with a minor in Computer Science. I am fascinated by the beautiful mathematics behind AI&ML systems. In particular, I am interested in understanding how simple rules can give rise to complex behaviors - whether that's in physics, mathematical systems, or modern AI. I think this perspective is especially relevant to the question of how we can ensure AI systems remain reliable and beneficial as they become more powerful, which I believe is an extremely important question.
Currently working as a Data Science Fellow at the UM Center for Academic Innovation
Publications
From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries
We introduce a novel course recommendation system that combines large language models with semantic search to bridge natural language queries and course descriptions. Our two-stage approach generates idealized course descriptions from student interests, then uses embedding similarity to identify relevant courses. Empirical evaluation demonstrates the system's ability to provide contextually appropriate recommendations with explanatory rationales.