Computer Science · UNSW Canberra

Adrian

Ph.D. candidate

Multimodal generative AI,
vision-language models, and industrial applications.

Portrait of Adrian
Canberra, Australia

I am a Ph.D. candidate in Computer Science at the University of New South Wales (UNSW), Canberra, advised by Prof. Huadong Mo and Prof. Daoyi Dong.

My research focuses on multimodal generative AI and vision-language models (VLMs), as well as their applications in industry. I am interested in controllable image and video generation, visual understanding, and multimodal reasoning. My background in industrial control and optimization informs how I approach the dynamics and practical constraints of industrial systems.

Ocean waves beneath a pastel evening sky
Beyond the lab Do Not Go Gentle into That Good Night

Research interests

Multimodal
generative AI

Controllable image and video generation, with a focus on consistent synthesis and editing.

Vision-language
models

Visual understanding and multimodal reasoning, including long-video analysis and VLM-based agents.

Industrial
applications

Exploring how generative models and VLMs can support industrial perception, modeling, and decision making.

I welcome collaborations on multimodal generation, vision-language models, and their applications in industry. Get in touch

Education

  • Ph.D. in Computer Science

    University of New South Wales

    2024 – Present
  • M.Eng. in Control Science & Engineering

    Beihang University

    2020 – 2023
  • B.S. in Weapon Science & Technology

    Beijing Institute of Technology

    2016 – 2020

News