Kerun Mi (米科润)

Master Student

Nanjing University of Science and Technology
Nanjing, Jiangsu, China

Email: kerun.mi [at] gmail.com

scholar github wechat twitter

avatar

Biography

Hello! I am a final-year Master's student at Nanjing University of Science and Technology, under the supervision of Prof. Chen Gong (IET Fellow). I obtained my B.S. at Xiangtan University in 2023.

My research interests lie in the intersection of Domain Adaptation and Continual Learning. Currently, I focus on exploring the transferability and anti-forgetting ability of Large Multimodal Models in open-world scenarios.

Feel free to contact me if you are interested in discussing or collaborating with me.

News

Selected Publications (*co-first author)

[Conference]
paper

Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation

Kerun Mi, Guoliang Kang, Guangyu Li, Lin Zhao, Tao Zhou, Chen Gong

The 33rd ACM International Conference on Multimedia (ACM MM), 2025.

(Oral Presentation)

[Paper] [Code] [中文解读]

 

Education

njust

Nanjing University of Science and Technology, China

Master of Computer Science

Advisor: Prof. Chen Gong

Sep. 2023 - Apr. 2026

 
xtu

Xiangtan University, China

Bachelor of Mathematics

Sep. 2019 - Jun. 2023

Selected Projects

[Software Copyright]

A PyTorch Optimizer Based on the Nonlinear Conjugate Gradient Method. Yangjin Cheng, Kerun Mi, Jiaoli Wang, Dingyi Luo. 2023SR0442637. GitHub stars

Honors & Awards

[06/2023] Outstanding Graduate: City-level & University-level award.
[04/2022] 3rd Prize — National College Student Market Survey and Analysis Competition: National-level award.
[09/2021] 2nd Prize — Contemporary Undergraduate Mathematical Contest in Modeling: Provincial-level award.

Professional Services

[Conference Reviewer]

International Conference on Computer Vision (ICCV) 2025
ACM International Conference on Multimedia (ACM MM) 2025

[Journal Reviewer]

IEEE Transactions on Image Processing (TIP)
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Chinese Journal of Electronics (CJE)

© Kerun Mi