Student looking to build real things at the intersection of ML research and applied systems.
I am a Mathematics & Computer Science student at the University of Illinois Urbana-Champaign, focused on continual learning for LLMs and practical data-driven products.
I build projects that combine mathematical modeling with machine learning engineering. My current work centers on making adaptation for large language models more efficient and practical.
In independent research, I developed Hierarchical Adapter Fusion, a continual learning framework that combines variational hypernetworks, FAISS-backed memory retrieval, and evolutionary candidate selection.
I enjoy shipping end-to-end systems, from experimentation and evaluation to production-oriented interfaces like APIs.
Education
Academic foundation and milestones.
University of Illinois Urbana-Champaign
Expected May 2030
B.S. Mathematics & Computer Science · Champaign, IL
West Shore Jr/Sr High School
May 2026
High School Diploma · Melbourne, FL
Valedictorian (Rank 1 / 132)
4.7 weighted GPA
Perfect ACT score
Dual enrollment at Florida Institute of Technology: Calculus III, Probability & Statistics, Discrete Mathematics, Algorithms & Data Structures
Research
Current and recent research tracks.
Hierarchical Adapter Fusion (HAF)
August 2025 - Present
Independent Research: Continual Learning for LLMs
Designed a continual learning framework combining a variational hypernetwork, FAISS-based hierarchical memory retrieval, and evolutionary candidate selection for parameter-efficient LLM adaptation.
Achieved approximately 15x lower adaptation cost compared with Self-Adapting Language Models.
1st Place, Brevard District Science FairMerit Award, Florida State Science Fair
I’m an incoming Mathematics & Computer Science student at the University of Illinois Urbana-Champaign with interests in machine learning, continual learning systems, and AI research. My work focuses on building scalable and efficient learning frameworks for large language models. I’ve conducted independent research in continual learning, developing Hierarchical Adapter Fusion (HAF), a framework combining hypernetworks, hierarchical memory retrieval, and evolutionary optimization for parameter-efficient LLM adaptation. I also enjoy applying AI and mathematical modeling to real-world problems. Recent projects include building a retrieval-augmented generation pipeline for financial data and developing a Markov chain model analyzing gambling addiction progression for the MathWorks Math Modeling Challenge. Beyond research, I’m interested in the intersection of mathematics, machine learning, and systems design, especially in areas involving efficient adaptation, reasoning, and long-term memory in AI systems. Technical interests: continual learning, retrieval-augmented generation (RAG), parameter-efficient fine-tuning, probabilistic modeling, and machine learning infrastructure.