Research identity first

I'm an incoming PhD student in Computer Science at Princeton University, starting in Fall 2026, where I will be advised by Tri Dao and Ravi Netravali. I previously worked as a Visiting Student Researcher at the Sky Computing Lab at UC Berkeley, advised by Ion Stoica, and also collaborated with Joseph E. Gonzalez and Matei Zaharia. I completed my B.S. in Computer Science (Turing Honors Class) at Renmin University of China.

I work broadly on machine learning systems, with interests in efficient infrastructure, training and inference systems, and the design of systems for emerging AI workloads.

Agenda

Research agenda

• Machine learning systems
• Training and inference infrastructure
• Efficient systems for AI workloads
• Systems support for emerging AI applications

Builder lens

Systems ideas into tools people use

Alongside research, I translate ML systems ideas into infrastructure and tools that people actually use — from a high-availability controller running in production to a vector index with tens of thousands of users.

On SkyPilot, I built the High Availability Controller for SkyServe — the layer that keeps model serving online across node and region failures — now adopted by startups including Hypermode. On LEANN, I led the push from research prototype to a low-storage vector index that runs on personal devices, with tens of thousands of downloads and a Best Paper Award at MLSys 2026.