Wengyu Zhang

Mike, 張翁漁

mike_photo.jpg

Department of Computing,

The Hong Kong Polytechnic University,

Kowloon, Hong Kong

I’m an Undergraduate Student at The Hong Kong Polytechnic University (PolyU), majoring in Computer Science, and a Student Assistant in the PolySmart Group of Research Centre on Data Sciences & Artificial Intelligence (RC-DSAI) at PolyU. My research interests include Computer Vision, Large Language Models, AI for Science as well as their practical applications in the real world.

I’m keen on self-learning, applying and transferring knowledge into practice. I’m the author of my blog website UltraFish.io and application website Plus.UltraFish.io, where I frequently update some articles as well as develop practical applications. My objective is to make AI accessible to everyone.

I regulate my life with self-discipline, my study with high quality, and my work with excellence.

I have many extra-curriculums experiences, including student assistant, research internship in the MIT Hong Kong Innovation Node, Hackathon, programming contests, and so on.

News

Jul 21, 2024 🎉 Our work Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval is accepted by ACM Multimedia 2024 as Oral presentation (top 3.97%).
Jul 21, 2024 🎉 Our work Generative Active Learning for Image Synthesis Personalization is accepted by ACM Multimedia 2024.
Jul 21, 2024 🎉 Our work A Picture Is Worth a Graph - A Blueprint Debate Paradigm for Multimodal Reasoning is accepted by ACM Multimedia 2024 as Oral presentation (top 3.97%).
Oct 21, 2023 I participated in PolyU Info Day 2023 and a Demo of AI Coffee System in RC-DSAI
May 15, 2023 I’m enrolled as a Student Assistant in the Research Centre for Data Sciences & Artificial Intelligence (RC-DSAI) at PolyU.

Selected publications

  1. ACM MM
    GAL_demo.jpg
    Generative Active Learning for Image Synthesis Personalization
    Xulu Zhang, Wengyu Zhang, Xiaoyong Wei, Jinlin Wu, Zhaoxiang Zhang, Zhen Lei, and Qing Li
    In ACM Multimedia 2024, 2024
  2. ACM MM
    LLMEPET_demo.jpg
    Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
    Yiyang Jiang, Wengyu Zhang, Xulu Zhang, Xiaoyong Wei, Chang Wen Chen, and Qing Li
    In ACM Multimedia 2024, 2024
  3. ACM MM
    BDoG_demo.jpg
    A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning
    Changmeng Zheng, DaYong Liang, Wengyu Zhang, Xiaoyong Wei, Tat-Seng Chua, and Qing Li
    In ACM Multimedia 2024, 2024