Kemou Li

Kemou Li

PhD Student

University of Macau

Research Interests

  • LLM Unlearning
  • Trustworthy AI
  • Machine Learning

Last Updated: 2026-07

About Me

Hi there! I am Kemou Li, a second-year PhD student in Computer Science at State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC), University of Macau, advised by Prof. Jiantao Zhou. Prior to that, I earned my BS degree in Mathematics from Sun Yat-sen University and MS degree in Artificial Intelligence from University of Macau. I also work closely with Dr. Fengpeng Li (KAUST), Dr. Qizhou Wang (RIKEN AIP), Prof. Haiwei Wu (UESTC), and Prof. Bo Han (HKBU).

My research broadly lies in trustworthy AI, with the goal of making modern machine learning systems more reliable, robust, and controllable. Earlier in my research, I worked on learning with noisy labels, adversarial training, and forgery detection. Now I am focusing on LLM unlearning, especially its theoretical foundations and its role in safer model release and post-training. I am also interested in LLM alignment, persona and behavior control, explainability, and agent security.

Outside of research, I enjoy staying active through long-distance running ๐Ÿƒ, basketball ๐Ÿ€, and swimming ๐ŸŠ. I am also quite good at Chinese calligraphy โœ๏ธ, playing the flute ๐ŸŽถ, and Chinese chess โ™Ÿ๏ธ. Beyond these, I am a rock music ๐ŸŽธ and film fan ๐ŸŽฌ, with Radiohead and David Lynch among my favorites.

I am always open to collaboration or exchanging ideas. Please feel free to contact me :-)

News

  • 2026-03 Our team wins the 6th place (6/535) at the NTIRE @ CVPR 2026: Robust AI-Generated Image Detection in the Wild Challenge.
  • 2026-02 One paper on image forensics accepted to CVPR 2026 Highlight (3.6%). See you in Denver!
  • 2026-01 Two papers on LLM unlearning and diffusion model concept erasure accepted to ICLR 2026. See you in Rio!
  • 2025-06 One paper on adversarial training accepted to IEEE TIFS.
  • 2025-06 Pass my PhD qualifying exam.
  • 2025-05 One paper on learning with noisy labels accepted to IJCV.
  • 2025-02 One paper on font watermarking accepted to IEEE TMM.
  • 2025-01 Start remote research at TMLR Group with Dr. Qizhou Wang and Prof. Bo Han.
  • 2024-09 One paper on adversarial training accepted to NeurIPS 2024.
  • 2024-09 Our team wins the championship (1/706) at the Global Multimedia Deepfake Detection Challenge (Image Track) at the 2024 Inclusion Conference on the Bund.
  • 2024-08 Start my PhD journey at the University of Macau.
  • 2023-12 One paper on learning with noisy labels accepted to AAAI 2024 Oral (2.2%).

Selected Publications

* = Equal Contribution

  1. LLM Unlearning with LLM Beliefs ICLR-26
    Kemou Li, Qizhou Wang, Yue Wang, Fengpeng Li, Jun Liu, Bo Han, Jiantao Zhou
    International Conference on Learning Representations (ICLR), 2026

Awards & Honors

Professional Services

Organizing Committee

Session Chair

APSIPA ASC 2024, Dec. 3-6, Macao, China

Conference Reviewer

NeurIPS 2025-2026 ICLR 2026 ICML 2026 CVPR 2026 ECCV 2026 AAAI 2027 ACM MM 2026 APSIPA ASC 2024-2025

Journal Reviewer

IEEE TIFS Knowledge-Based Systems

Teaching Experience

Teaching Assistant

University of Macau

I have supported both postgraduate (PG) and graduate (G) courses in artificial intelligence, machine learning, multimedia, and image processing.

CISC8001 PG
Spring 2026

Principles of Artificial Intelligence

GEST1009 G
Fall 2025

Multimedia Technology in Modern Society

CISC7202 PG
Spring 2025

Tools for Machine Learning

CISC7014 PG
Fall 2024

Advanced Topics in Computer Science (Image Processing and Pattern Recognition)