Research Interests
AI for Science
Leveraging machine learning to advance scientific discovery by understanding physical laws, modeling complex systems, and extracting insights from scientific data across genomics, physics, and materials science.
Computational Physics & Modeling
Building machine learning models to simulate, predict, and optimize physical phenomena. Focus on scientific machine learning approaches that respect physical constraints and domain knowledge.
ML Systems & Applications
Designing robust, scalable machine learning systems for NLP, real-world applications, and education. Passionate about supporting underrepresented groups in tech through accessible tools and knowledge sharing.
Research Projects
Capstone: NLP for Course Evaluation Analysis
OngoingBuilt an NLP pipeline to analyze and summarize course evaluations, extracting actionable insights from noisy, unstructured feedback. Evaluated summarization and sentiment models across datasets (CSUMB, UCLA), designing metrics to measure performance and generalization. Developed a benchmarking framework to compare model outputs and assess insight quality across diverse evaluation formats.
PAT: Pangenome Annotation Toolkit
OngoingPAT is a scalable pipeline that merges annotations from multiple source genomes into a unified graph coordinate set to rapidly annotate any newly added assembly to the graph. Poster Link
