Zhengbo Wang (王政博)

zb_prof_pic.jpg

Hi there (。・∀・)ノ゙.

I am a Ph.D. student at University of Science and Technology of China, under the supervision of Prof. Tieniu Tan and co-supervision of Prof. Jian Liang, Prof. Ran He and Prof. Zilei Wang. Before that, I earned my BS in Electronic Information Engineering from University of Science and Technology of China in 2021.

My current research focuses on developing safe, robust, and efficient fine-tuning methods for vision-language models and large language models. See also my list of publications.

You can download my CV here.

Email is the best way to reach me: zhengbowang@mail.ustc.edu.cn. Feel free to send me a message!

Education

University of Science and Technology of China
School of Information Science and Technology
PhD student, 2021 - present
University of Science and Technology of China
School of Information Science and Technology
Undergraduate, 2017 - 2021

News

May 07, 2024 I attended the ICLR 2024 in Vienna. 🤪🤪🤪
May 02, 2024 Two of our paper have been accepted at ICML 2024! 🤯🤯🤯
Jan 15, 2024 Our paper “A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation” has been accepted by ICLR 2024! Code is available now! 😊😊
Sep 06, 2023 We achieved 1st place in the UniDA track of the GeoNet competition at ICCV23! 😀😀
Jul 14, 2023 Our paper “Improving Zero-Shot Generalization for CLIP with Synthesized Prompts” has been accepted by ICCV 2023! 🥳🥳🥳

Publications

  1. ICLR
    A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
    Zhengbo WangJian LiangLijun ShengRan HeZilei Wang, and Tieniu Tan
    In The Twelfth International Conference on Learning Representations , 2024
  2. ICCV
    Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
    Zhengbo WangJian LiangRan He, Nan Xu , Zilei Wang, and Tieniu Tan
    In Proceedings of the IEEE/CVF International Conference on Computer Vision , 2023
  3. ICASSP
    Exploiting Semantic Attributes for Transductive Zero-Shot Learning
    Zhengbo WangJian LiangZilei Wang, and Tieniu Tan
    In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing , 2023
  4. ICML Spotlight
    Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
    Jian LiangLijun ShengZhengbo WangRan He, and Tieniu Tan
    In Forty-first International Conference on Machine Learning , 2024
  5. ICML
    Connecting the Dots: Collaborative Fine-tuning for Black-Box Vision-Language Models
    Zhengbo WangJian LiangRan HeZilei Wang, and Tieniu Tan
    In Forty-first International Conference on Machine Learning , 2024
  6. ICCVW
    Self-training solutions for the ICCV 2023 GeoNet Challenge
    Lijun ShengZhengbo Wang, and Jian Liang
    arXiv preprint arXiv:2311.16843, 2023
  7. Preprint
    LoRA-Pro: Are Low-Rank Adapters Properly Optimized?
    Zhengbo Wang, and Jian Liang
    arXiv preprint arXiv:2407.18242, 2024

zhengbo.wang