
Hi, welcome to my website! :)
Research
My research explores efficiency problems in machine learning from systems, algorithms, and data perspectives, with a focus of reducing unnecessary computational barriers. I work on fundamental questions about how intelligent algorithmic design can eliminate resource requirements that limit broader participation in AI development and deployment.
Currently, I'm investigating several interconnected approaches: agreement-based methods for efficient model routing, forward-pass techniques for model compression, and semantic approaches to extracting parallelism from natural language queries. My broader research vision centers on demonstrating that accessibility and performance are not opposing forces; that thoughtful design choices can achieve both.