Leeon . kk

Affiliations. Li Auto. lichangkang@buaa.edu.cn .

japan.jpg

I received my M.S. degree from Beihang University (BUAA), Beijing, China, and my B.S. degree from Huazhong University of Science and Technology (HUST), Wuhan, China, in 2022.

My research interests lie in the following areas:

  • Efficient LLM Inference and Systems
  • Large Language Model Reasoning
  • Computer Vision and Image/Video Anomaly Detection
  • Vision-Language Models

Work Experience

AI Infrastructure Engineer, Li Auto Inference Framework Development | July 2025 - Present

Machine Learning Platform, Kuaishou LLM Inference Optimization | May 2025 - October 2025

  • Focused on optimizing inference latency for large language models within the Social Sciences division

TPG Paddle, Baidu Hardware Adaptation and Acceleration | December 2024 - April 2025

  • Worked on hardware adaptation and performance acceleration for PaddlePaddle

news

Jul 20, 2024 🎉 Our research paper on Vision-Language Models for Video Anomaly Detection has been accepted by BMVC 2024. :sparkles: :smile: I will be in Glasgow, UK for BMVC 2024 on November 25th for BMVC 2024! Hope to meet many of you there! 🤗🤗
Jul 01, 2024 🎉 My personal homepage has been established for the first time.

Publications

  1. vlavad.png
    VLAVAD: Vision-Language Models Assisted Unsupervised Video Anomaly Detection
    Changkang Li, and Yalong Jiang
    In BMVC , 2024
  2. reasonvad.jpg
    Reasonable Anomaly Detection Based on Long-term Sequence Modeling
    Yalong Jiang, Changkang Li, Wenrui Ding, and 2 more authors
    IEEE Transactions on Circuits and Systems for Video Technology, 2024
  3. physical.jpg
    A Physically Explainable Framework for Human-Related Anomaly Detection
    Yalong Jiang, Huining Li, and Changkang Li
    In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2023