Kai Liu

profile_image.jpg

Zhejiang University

Hangzhou, 38 Zheda Road.

Email: kail@zju.edu.cn

I am a Ph.D. student at the College of Biomedical Engineering and Instrument Science, Zhejiang University, during the supervision from Prof. Fan Zhou and Prof. Yaowu Chen from 2020 to present. I am currently a research intern at Apsar Lab, Alibaba Cloud.

My research interests lie in uncertainty estimation, open-world learning, middle-level image analysis (recognition, detection, tracking, etc.), vision-language applications, and large language models. I’m always looking for related collaboration. If you are interested to chat with me, feel free to drop me an email. Here is my CV.

Listed below are the accepted papers in top conferences and journals where I worked as the first author. Here are the full lists of publications and the repositories will come soon. I look forward to continuing to make valuable contributions to computer vision as well as natural language processing.

news

Feb 4, 2024 More ArXiv papers and GitHub repositories are coming soon!
Feb 1, 2024 Recipient of Alibaba Cloud’s Outstanding Research Intern Award (top-5%)!
Jan 15, 2024 One paper is accpted by ICLR’24!
Dec 14, 2023 Two papers are accpted by NeurIPS’23!
Jul 14, 2023 My first paper U2MOT was accpted by ICCV’23!

selected publications

  1. iclr24_inside.png
    INSIDE: LLMs’ Internal States Retain the Power of Hallucination Detection
    Chao Chen, Kai Liu, Ze Chen, Yi Gu, Mingyuan Tao, Zhihang Fu, and Jieping Ye
    In International Conference on Learning Representations, May 2024
  2. nips23_catex.png
    Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions
    Kai Liu, Zhihang Fu, Chao Chen, Sheng Jin, Ze Chen, Mingyuan Tao, Rongxin Jiang, and Jieping Ye
    In Conference on Neural Information Processing Systems, Nov 2023
  3. iccv23_u2mot.png
    Uncertainty-aware Unsupervised Multi-Object Tracking
    Kai Liu, Sheng Jin, Zhihang Fu, Ze Chen, Rongxin Jiang, and Jieping Ye
    In International Conference of Computer Vision, Oct 2023