ZHU LEI (祝磊)

HK_2018.jpg

I got my PhD degree from CityUHK under the supervision of Prof. Rynson W.H. Lau in July, 2024. Before that, I received my bachelor degree in Computer Science and Engineering from Dalian University of Technology (rank 1/102) and spent one year as PhD student at CUHK under the supervision of Eric Lo.

My research focus on hardware-efficient architecture design, LLM inference acceleration, and (vision)-language foundation models. Before finalizing PhD research topic on effective attention mechanisms, I actively explored several topics such as 3D vision, data-efficient learning and low-level vision. Through all these trials, I have built a good understanding on GPUs, deep learning systems, and strong skills on experiment automation. During the journey, I published 8 papers in top venues (including 4 first-author ones), and earned 750+ citations (640+ from first-author papers).

News

Oct 30, 2024 I’m pleased to receive NeurIPS travel award and be selected as Top Reviewers.
Sep 26, 2024 One first-author paper on vision backbone is accepted by NeurIPS 2024.
Jul 02, 2024 I passed my oral defense and became a Dr.
Jul 02, 2024 One co-authored paper (Analytic-Splatting) is accepted by ECCV 2024.
May 16, 2024 RelayAttention got accepted by ACL 2024 main conference.

Selected Publications

  1. ACL
    acl2024_relayattention.png
    RelayAttention for Efficient Large Language Model Serving with Long System Prompts
    Lei Zhu, Xinjiang Wang, Wayne Zhang, and 1 more author
    In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2024
  2. CVPR
    biformer_cvpr23.png
    BiFormer: Vision Transformer with Bi-Level Routing Attention
    Lei Zhu, Xinjiang Wang, Zhanghan Ke, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023