Avatar
Qijun Luo 罗琪竣
Ph.D. student in computer information engineering
The Chinese University of Hong Kong, Shenzhen

Biography

I am a final year PhD student at The Chinese university of Hong Kong, Shenzhen (CUHKSZ), supervised by Prof. Xiao Li. Before that, I obtained my bachelor degree in computer science from CUHKSZ in 2021.

My research interest lies in Efficient AI, i.e. improving the training/inference efficiency of LLM. I achieve this goal by designing efficient optimization algorithms (e.g. [1, 2, 3]) and training infrastructures (e.g. [4]).

Contact: qijunluo at link.cuhk.edu.cn

Selected Publications

A collection of recent works. See my Google Scholar for the latest research outcomes.

  • ARO: A New Lens On Matrix Optimization For Large Models. [arXiv]
    Wenbo Gong, Javier Zazo, Qijun Luo, Puqian Wang, James Hensman, Chao Ma.

  • StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs. [arXiv] [code]
    Qijun Luo, Mengqi Li, Lei Zhao, Xiao Li.
    Advances in Neural Information Processing Systems (NeurIPS), 2025.

  • Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Correction.
    Qijun Luo, Yifei Shen, Liangzu Peng, Dongsheng Li, Xiao Li.
    Advances in Neural Information Processing Systems (NeurIPS), 2025.

  • BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models. [OpenReview] [arXiv] [code]
    Qijun Luo, Hengxu Yu, Xiao Li.
    Advances in Neural Information Processing Systems (NeurIPS), 2024.

  • Finite-Time Analysis of Fully Decentralized Single-Timescale Actor-Critic. [arXiv] [OpenReview]
    Qijun Luo, Xiao Li.
    Transactions on Machine Learning Research (TMLR), 2023.

Research Experiences

  • Microsoft Research Cambridge. Research Intern, 2025.6–2025.9
    • Topic: optimizer design for effective LLM pre-training.
  • Microsoft Research Asia. Research Intern, 2024.7–2024.12
    • Topic: Memory-efficient post-training of LLM.
  • Huawei Noah’s Ark Lab. Research Intern, 2019.10–2020.9
    • Topic: Transfer learning.

Awards

  • NeurIPS scholar award (2024)
  • Top reviewer @ NeurIPS (2024)
  • PhD fellowship, Shenzhen research institute of big data (2022-2023)
  • Teaching assistant award, school of data science, CUHKSZ (2023)

Services

Reviewer:

  • ICLR (2024-2025)
  • ICML (2025)
  • NeurIPS (2024-2025)
  • TMLR (2024-2025)
  • SIMODS (2024)

Teaching Experiences

  • MDS5210: Machine Learning. Teaching Assistant, 2022 spring & fall, 2023 fall, 2024 fall
  • MAT3007: Optimization I. Teaching Assistant, 2021 fall & summer