Zhuojin Li

About me

I am a PhD candidate at Quantitative Evaluation & Design (QED) research group of University of Southern California (USC) advised by Prof. Leana Golubchik. My research focuses on performance evaluation of AI systems, particularly in edge and mobile systems with limited computing capabilities, as well as in distributed training environments. I received my M.S. in Computer Science from University of Southern California in 2020, and my B.S. in Computer Science from Peking University in 2018.

Experiences

• Research Intern
  Neural Architecture Search, Qualcomm AI Research
  May 2023 - Aug 2023
• Teaching Assistant
  CSCI 402, Operating Systems, Instructor: Bill Cheng
  Spring 2020 - Fall 2024

Publications

• Zhuojin Li, Marco Paolieri, and Leana Golubchik:
  Inference Latency Prediction for CNNs on Heterogeneous Mobile Devices and ML Frameworks
  Performance Evaluation, Volume 165, 2024
• Zhuojin Li, Marco Paolieri, Leana Golubchik:
  A Benchmark for ML Inference Latency on Mobile Devices
  Proceedings of the 7th International Workshop on Edge Systems, Analytics and Networking, 2024
• Zhuojin Li, Marco Paolieri, Leana Golubchik:
  Predicting Inference Latency of Neural Architectures on Mobile Devices
  Proceedings of the 2023 ACM/SPEC International Conference on Performance Engineering (ICPE), 2023
• Zhuojin Li, Marco Paolieri, Leana Golubchik, Sung-Han Lin, Wumo Yan:
  Predicting Throughput of Distributed Stochastic Gradient Descent
  IEEE Transactions on Parallel and Distributed Systems, 2022
• Zhuojin Li, Wumo Yan, Marco Paolieri, Leana Golubchik:
  Throughput Prediction of Asynchronous SGD in TensorFlow
  Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE), 2020