I am a Ph.D. candidate in Computer Engineering at Virginia Tech, advised by Prof. Lingjia Liu, and a visiting researcher at Argonne National Laboratory within the Mathematics and Computer Science (MCS) division, where I work closely with Robert Underwood, Sheng Di, and Franck Cappello. My research lies at the intersection of information theory, machine learning, statistical modeling, and large-scale computing systems, with a focus on developing mathematically grounded methods for representing, compressing, and learning from high-dimensional data at scale.

During my Ph.D., I developed the first information-theoretic frameworks for characterizing the fundamental limits of scientific lossy compression under realistic high-performance computing (HPC) constraints. This work bridges a long-standing gap between classical rate-distortion theory and the practical design of production scientific compressors used in exascale computing systems. Building on these foundations, my current research extends rate–distortion principles to foundation models, including large language models (LLMs) and large-scale vision models, through tokenized representation learning frameworks that study the tradeoffs between data, compression, model capacity, and compute in modern machine learning systems.