Shangge Liu
Services
Awards
Frameworks
Publications
Preprints
About Me
Photo

Shangge Liu

Master Student
Reasoning & Learning Group
School of Computer Science
State Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210023, China
Email: lshangge@smail.nju.edu.cn

Supervisor
Master: Professor Wenbin Li

Current Research Topics
  • Machine Learning
  • Continual Learning
  • Model Merging

About Me

I am currently a Master student in the School of Computer Science at Nanjing University, supervised by Wenbin Li. I am a member of the Reasoning and Learning Research Group, led by Professor Yang Gao. Previously, I received my bachelor's degree from Beijing Institute of Technology in 2024.

News

[2026-02] One paper is accepted by Neural Networks (NN) 2026.
[2026-02] One paper is accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026.

Preprints

LibContinual: A Comprehensive Library towards Realistic Continual Learning.
Wenbin Li, Shangge Liu, Borui Kang, Yiyang Chen, KaXuan Lew, Yang Chen, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo.
ArXiv 2025 [Paper] [Code]

Publications

(# indicates equal contribution, * indicates corresponding authorship)

A Continual Learning Framework with Long-term and Multiple Short-term Memory Networks.
Shangge Liu, Lei Wang, Rui Yan, Jing Huo, Wenbin Li*, Yang Gao.
Neural Networks (NN) 2026. [Paper] [Code]
Understanding and Enforcing Weight Disentanglement in Task Arithmetic.
Shangge Liu, Yuehan Yin, Lei Wang, Qi Fan, Yinghuan Shi, Wenbin Li*, Yang Gao, Dacheng Tao.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026. (AC Rate = 25.4%) [Paper] [Code]
LaST-LoRA: Adaptive Knowledge Reuse and Latent Subspace Tracking for Continual Learning.
Shangge Liu, KaXuan Lew, Yuhang Zhu*.
ACMMM CL' 25 [Paper] [Code]

Frameworks

  • LibContinual is a comprehensive library for continual learning, especially for continual image classification. It integrates multiple classic continual methods into a unified framework. This library is friendly for beginners in continual learning with very concise code and clear structure.

Awards

    2025
    Outstanding Graduate Student, Nanjing University
    南京大学优秀研究生
    2025
    Excellence in Master's Assessment, Nanjing University
    南京大学硕士考核卓越
    2025
    Xiaomi Scholarship
    小米奖学金
    2024
    Outstanding Graduates of Beijing
    北京市优秀毕业生
    2023
    National Scholarship
    国家奖学金
    2022
    Merit Student of Beijing
    北京市三好学生
    2022
    National Scholarship
    国家奖学金

    Other awards during undergraduate studies 本科期间其他奖项

  • 北京理工大学(最高荣誉奖学金)徐特立奖学金提名，2024
  • 第二届CCF“司南杯”量子计算编程挑战赛，全国一等奖，2023
  • 全国大学生计算机系统能力大赛操作系统赛，区域赛三等奖，2022
  • 第20届全国大学生信息安全与对抗技术竞赛，全国二等奖，2023
  • 北京市大学生电子设计竞赛，北京市三等奖，2022
  • 第十届全国大学生光电设计竞赛，全国三等奖，2022
  • 第八届中国国际互联网+大学生创新创业大赛，北京市一等奖，2022
  • RoboMaster机甲大师超级对抗赛，全国三等奖，2022
  • 全国大学生数学建模竞赛，北京市二等奖，2021
  • 第十三届全国大学生数学竞赛（非数学类），全国二等奖，2021

Correspondence

Email: lshangge@smail.nju.edu.cn

Address: Shangge Liu, National Key Laboratory for Novel Software Technology, Nanjing University, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China.