Zhongming Yu

UCSD CSE. Ph.D.

prof_pic.jpg

San Diego, California

I am a third-year Ph.D. advised by Prof. Jishen Zhao in Computer Science and Engineering Department of UC San Diego, starting in 2022. I am now aiming to build efficient systems for machine learning. Before coming to UCSD, I received my B.E. degree from the Department of Electronic Engineering at Tsinghua University. I have a broad interest in combining machine learning and computer systems, with a special focus on the interaction between ML and System. I have previously focused on more acceleration for sparse computing (e.g. GNN, Pointcloud acceleration) and devoted myself to some open-source projects like dgSPARSE and CogDL. Now I am working on agent framework that could help design better system, especially moving to MLsys self-evolution. Some topics that I have been working on are listed below:

  • LLM Agent System for MLSys
  • Machine Learning Compiler
  • High-performance GPU Kernels
  • Autonomous Software Engineering (SWEBench)

Feel free to contact me if you share any common interests.

news

Feb 6, 2025 We just released our software issue localization framework OrcaLoca, check it out at Github.
Dec 10, 2024 We published our LLM4RTL project on arxiv! Check it out at MAGE.

selected publications

  1. mlsys
    Understanding gnn computational graph: A coordinated computation, io, and memory perspective
    Hengrui Zhang*, Zhongming Yu*, Guohao Dai, and 4 more authors
    Proceedings of Machine Learning and Systems, 2022
    * stands for equal contribution
  2. mlsys
    HyperGef: A Framework Enabling Efficient Fusion for Hypergraph Neural Network on GPUs
    Zhongming Yu, Guohao Dai, Shang Yang, and 6 more authors
    Proceedings of Machine Learning and Systems, 2023
  3. mlsys
    Exploiting Hardware Utilization and Adaptive Dataflow for Efficient Sparse Convolution in 3D Point Clouds
    Ke Hong*, Zhongming Yu*, Guohao Dai, and 4 more authors
    Proceedings of Machine Learning and Systems, 2023
    * stands for equal contribution