I am a PhD Candidate in Computer Science at Columbia University advised by Prof. Smaranda Muresan. My research focuses on sociotechnical AI alignment. Human values are neither uniform nor explicit, yet current AI systems largely model what's on the surface. I have approached this problem along two lines of work: modeling human subjectivity (e.g., variation in expert and crowd annotation) and understanding pragmatics — implicit knowledge required to interpret stylistic appropriateness, metaphor, and socio-cultural norms in text, images, and videos. Along these lines, I have built methods and benchmarks that require models to explain their reasoning, evaluating alignment beyond surface agreement.
During my graduate studies, I interned twice at Google DeepMind and at AWS AI. Before starting my PhD, I completed my B.A. at Columbia College and worked as a data scientist at UBS.
