Grad student exploring AI to improve how we learn and work.
I'm a Computer Science Ph.D. student at UC Santa Barbara, advised by Xifeng Yan, applying AI/ML to real-world problems, from LLM-aided database verification to accessible interfaces for retinal implants.
An improvement of GEPA (automatic prompt optimization) through "hyper-reflection", enabling compact LLMs to achieve performance closer to frontier models on complex tasks like SQL query equivalence generation and refutation.
DBDoctor uses LLMs to propose counterexamples and rewrite queries into SMT-friendly forms, dramatically reducing the rate of "unsupported" query pairs from 100% to 1% and successfully refuting 47% of previously unverifiable cases.
A research project optimizing visual symbol sets for patients with retinal implants. By analyzing confusion matrices over simulated letter recognition using the pulse2percept framework, SymbolSight derives symbol sets that remain distinguishable even under the severe distortions introduced by low-resolution prosthetic vision.
A graph neural network approach to predicting missing nutrient values in food composition databases. By building a knowledge graph enriched with LLM-derived semantic relations between foods, NutriGNN improves representation learning and prediction quality, especially for low-resource food items with sparse nutritional data.
