I am a PhD student in the Operations Research Center (ORC) and Laboratory for Information and Decision System (LIDS) at MIT. I am advised by Professor Patrick Jaillet and Professor Chara Podimata. Prior to my PhD, I graduated from Purdue University with a B.S. degree in Mathematics Honor and Statistics Honor. My undergraduate research advisor is Professor Jonathon Peterson.
I am a person who really enjoys doing research. Doing research is a lot of fun! My research interest includes online learning and optimization, revenue management, stochastic process, probability theory, and game theory. Recently, collaborated with Microsoft Research, my research direction is on Optimization in Large Language Model (LLM) Inference. The LLM inference involves the computational techniques and strategies used to process input prompts and generate responses through a large language model. This field intersects significantly with online optimization, particularly in areas like online batching, scheduling, and resource allocation. Given the substantial costs associated with LLM inference—for instance, ChatGPT incurs about $500,000 daily—I aim to reduce these expenses by optimization. I have developed a foundational model for LLM inference and introduced scheduling and batching algorithms with constant regret. Over the next five years, I will continue advancing research in this area.
I am very happy to collaborate with different people. If you have research project lies in my interest, feel free to reach out to me! I also welcome undergraduate students who have similar research interests to talk with me. We can find some interesting topics to work together!
I am also interested in playing the piano, playing basketball, hiking, traveling, cooking, wine tasting, reading history books, and watching cartoon. My favorite musician is Chopin. My favorite basketball player is Stephen Curry. In addition, I am a big fans of Pokemon for more than fifteen years!