BUILDING
TECHNOLOGY
THAT MATTERS

Language shapes how we see the world — yet most of today's AI speaks only a handful of them fluently. Working with Dr. Zoey Liu, I investigate how data partitioning strategies on LLM training data impact model generalization across the world's linguistic diversity, with a particular focus on low-resource languages that are systematically underrepresented in modern AI.

My current work quantifies a fundamental trade-off: how much does annotation quality matter when data is scarce? By systematically injecting controlled annotation noise into training sets and benchmarking OLMo-2 across 2,000 languages on UF's HiPerGator supercomputer, I'm building an empirical map of where AI breaks down — and how to fix it.

Quality vs. Quantity

Systematically modeling the trade-off between dataset scale and annotation fidelity — a fundamental question with outsized implications for languages where data is precious.

2,000 Languages Tested

Benchmarking across a typologically diverse language set to understand how massive multilingual scale affects cross-linguistic transfer beyond high-resource language clusters.

Morphological Segmentation

Investigating cross-lingual partitioning of morphologically segmented data across language families to improve zero-shot performance for understudied tongues.

AI Career Coach

Resume Optimizer & Interview Simulator

End-to-end AI career prep tool: Gemini-powered ATS-compliant resume generation, mock interview engine with performance persistence, and automated weekly industry skill & salary trend updates via Inngest workflows.

Home Price Estimator

Data Structures · Full-Stack

Full-stack web app delivering neighborhood housing price estimates at 98% accuracy. Implements Red-Black Tree and B-Tree structures to query 100,000+ records in O(log n) time — a C++ backend connected to a React frontend via Next.js.