Mingjia Shi

Mingjia Shi

↑ This guy has just finished research works and is now in the gym. [Casual]

Mingjia (Samuel Jayden) Shi’s Homepage.

If you think the left ones are too casual, I have a formal version too. You should focus more on the content below than here!

Biography

  • It’s the 2nd year (written in 2024) as an intern student in NUS HPC-Lab, and I enojoy the challenges and interesting topics here (e.g. efficient AI, generative model, parameter generation and etc.).
  • From Sep. 2021 to June. 2024, I completed my master degree at Sichuan University majored in Artificial Intelligence, right where I had completed my 4-year bachelor’s degree before, supervised by Prof. Jiancheng Lv. The majors of my career in Sichuan University are distributed optimization and learning (e.g., decentralized optimization and federated learning).

Latest News

  • DDLs After. Waiting for 2025 Fall PhD Interviews.
  • DDLs Before. Actively applying for a 2025 Fall PhD! If you are interested in a student familiar with theoretical analysis, generative model with extensive industry experiences as well, feel free to Mail!

Current areer

During my research period, as an author and a reviewer of Top AI conferences and journals, I have appreciated the fascination and what I want to do, so I pursue a PhD career further.

Research Interests

  • Works in hands. My works are mainly both theoretical analyses and corresponding methods about Efficient AI on Trends, Generative Models, AI Privacy and Safety and Federated Learning.
  • Overall background. A knowledge and research background about math+cs, system/control/information theory, deep learning thoeries, optimization and generalization.
  • Addition. There is a continuing interest in technical research as well as basic science research. Physics and other science disciplines are always beautiful.

Selected Publications

2024 and Before

[Released Pre-Print]

  1. Arxiv Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-training. Arxiv. M. Shi*, Y. Zhou*, R. Yu, Z. Li, Z. Liang, X. Zhao, X. Peng, T Rajpurohit, R. Vedantam, W. Zhao, K. Wang, Y. You. (paper, code, page)
  2. Arxiv Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation. X. Wu, J. Niu, X. Liu, M. Shi, G. Zhu, S. Tang (paper)
  3. Arxiv A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training. K. Wang*, Y. Zhou*, M. Shi*, Z. Yuan, Y. Shang, X. Peng, H. Zhang, Y. You (paper, code)

[Conference]

  1. ICASSP 2024 Federated CINN Clustering for Accurate Clustered Federated Learning. Y. Zhou, M. Shi, Y. Tian, Y. Li, Q. Ye, J. Lv (paper)
  2. NeurIPS 2023 PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning. M. Shi, Y. Zhou, K. Wang, H. Zhang, S. Huang, Q. Ye, J. Lv (paper, code)
  3. ICONIP 2023 Unconstrained Feature Model and Its General Geometric Patterns in Federated Learning: Local Subspace Minority Collapse. M. Shi, Y. Zhou, Q. Ye, J. Lv (paper)
  4. ICCV 2023 Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence. Y. Zhou, M. Shi, Y. Li, Y. Sun, Q. Ye, J. Lv (paper)

[Journal]

  1. InfoSci DeFTA: A Plug-and-Play Peer-to-Peer Decentralized Federated Learning Framework. Y. Zhou, M. Shi, Y. Tian, Q. Ye, J. Lv (paper)
  2. Trans.ETCI DLB: a dynamic load balance strategy for distributed training of deep neural networks. Q. Ye, Y. Zhou, M. Shi, Y. Sun, J. Lv (paper)
  3. JoSc FLSGD: free local SGD with parallel synchronization. Q. Ye, Y. Zhou, M. Shi, J. Lv (paper)