👋 Call me Joshua.

🎓 I’m a second-year CS Ph.D. student at CSAIL, MIT EECS, advised by Samuel Madden. I’m a member of MIT CSAIL Everest Lab and LMCache Lab. I have been fortunate to work with Omar Khattab, Junchen Jiang, Ravi Netravali, Kexin Pei, and Ganesh Ananthanarayanan. Previously, I graduated from the University of Chicago with B.S. in Mathematics and Computer Science.

👨‍💻 My primary research interests lie broadly in systems and artificial intelligence for mid- and post-training, inference, and inference-time scaling of language models (LMs) and agents. My recent work focuses on 1) RL-based mid-/post-training and test-time scaling, 2) recursive self-improvement, and 3) AI query engines for agentic search. I’ve also worked on 4) high-performance KV cache management for LM serving.

In a fruitful and diverse previous life, I was a research engineer on the founding team of Tensormesh (creator of LMCache). During my undergraduate years, I began research in mathematics, advised by Gregory Lawler and Jinwoo Sung, and worked on probability theory.

Feel free to shoot me an email to talk about anything. I am always open to collaborations and working with undergraduate/master’s students. Check out Collaborations for details.

Education

• Ph.D. in Computer Science, Massachusetts Institute of Technology, 2025-present
• B.S. in Mathematics (with Specialization in Economics) and Computer Science, University of Chicago, 2022-2025

More About Me

I grew up in Guangzhou (Canton) and Hong Kong before moving to Washington, D.C. for high school.
I speak English, Cantonese, and Mandarin fluently, and a little bit of Hakka and Spanish.
I love piano and classical music. A lot. For piano, I mainly play Beethoven and Chopin, and sometimes Saint-Saëns and Mozart.
I love sports. Also a lot. I played varsity soccer and basketball in high school, and I follow all kinds of sports, from soccer and basketball to tennis, golf, F1, etc. I’m a fan of Borussia Dortmund 💛🖤.
I also love movies, astronomy, food, etc.

To be continued…