Jian Chen

I am a second-year M.S. student in ECE at Carnegie Mellon University, where I am working on efficient LLM serving under the supervision of Prof. Beidi Chen. Previously, I worked with Prof. Ding Zhao on research in generalizable reinforcement learning. I completed my bachelor’s degree at Zhejiang University, where I had the privilege of being advised by Prof. Xunzhao Yin. Additionally, I gained research experience as a research intern at UC Davis, where I was supervised by Prof. S.J. Ben Yoo.

Email  /  Google Scholar  /  Github  /  Linkedin

Research

I am interested in machine learning and computer systems, currently focused on developing scalable, hardware-aware algorithms and systems to accelerate large machine learning models. Previously, I conducted research in generalizable reinforcement learning and hardware acceleration for machine learning.

A comprehensive analysis of LLM inference performance and speculative decoding speedup, identified that speculative decoding can achieve both low latency and high throughput for moderate to long sequences with an intelligent speculation strategy.

An algorithm utilizes low-rank Markov Decision Processes to capture causal transition dynamics, effectively addressing objective mismatch caused by distribution shifts in offline Model-based Reinforcement Learning.

A novel Compute-in-Memory crossbar design utilizing Ferroelectric Transistors to enable non-von Neumann hardware acceleration of Multiply-and-Accumulate operations in Neural Networks.

Education

• GPA: 3.96/4.0
• Course assistant of 24-677 Modern Control for Robotics and 24-784 Trustworthy AI

• GPA: 3.83/4.0
• Zhejiang University Scholarship (2019, 2020)

last update: Nov 4, 2024

Copy from Dr. Jon Barron's page.