I'm Huanyu Wang (王焕宇), a 4th-year undergraduate at Shanghai Jiao Tong University, pursuing dual degrees in Computer Science and Applied Mathematics.
I am currently advised by Prof. Zhouhan Lin at the LUMIA Lab. Starting in Fall 2026, I will join Prof. Beidi Chen's InfiniAI Lab at Carnegie Mellon University as a Ph.D. student.
Outside of research, I enjoy basketball, Japanese anime, and traveling. I also live with a lovely cat named Mao-na.

Research Interests
- Efficient Inference Token compression and KV cache optimization for efficient LLM/VLM serving.
- Decentralized Systems Cross-region collaboration between heterogeneous AI services.
- ML Systems & HPC Kernel- and system-level optimization across modern hardware.
News
New preprint: WWW.Serve,
a decentralized and collaborative multi-LLM serving framework.
New preprint: DynaKV,
a token-wise adaptive KV cache compression method.
New preprint: Fourier Compressor,
a frequency-domain VLM token compression approach.
Selected Publications
Education
Carnegie Mellon University
Ph.D. in Electrical and Computer Engineering
Starting from Fall 2026
Shanghai Jiao Tong University
B.E. in Computer Science and Technology (IEEE Honor Class)
B.S. in Mathematics and Applied Mathematics (Dual degree)
Sept. 2022 - Jun. 2026 (Expected)



