ZhihuAbout Me
I am Chunyang (Cedric) Zhang, a Ph.D. candidate in Computer Science at the University of New South Wales (UNSW), Canberra. Supervised by Prof. Daoyi Dong and Prof. Huadong Mo, my research sits at the intersection of Generative Models and Modern Optimization.
My long-term goal is to build embodied AI systems that act reliably in the physical world. I am especially interested in Vision–Language–Action (VLA) models — combining the perceptual and reasoning capacity of large generative models with the decision-making rigor of optimization and control. I believe the next leap in real-world deployment will come from systems that not only generate plausible behavior, but also optimize it under physical, safety, and resource constraints.
Education
- Ph.D. in Computer Science, UNSW Canberra 2024 – Present
- M.Eng. in Control Science & Engineering, Beihang University 2020 – 2023
- B.S. in Weapon Science & Technology, BIT 2016 – 2020
Research Interests
- Embodied AI & VLA: Vision–Language–Action models, world models, and policy learning for real-world robotics and autonomous systems.
- Generative Modeling: Diffusion models, video generation, and consistent multi-instance synthesis.
- Optimization & Control: Reinforcement learning, distributed optimization, and intelligent control for safe and efficient deployment.
- AI for Science: Physics-informed machine learning as a bridge between data-driven models and first-principle constraints.
I am actively seeking collaborations with peers working on bringing generative intelligence into closed-loop, real-world systems.
News
- [Feb. 2024] Joined the School of Systems and Computing at UNSW as a Ph.D. candidate.
- [Aug. 2023] Our paper “Robust Control of Multi-Line Re-Entrant Manufacturing Plants…“ was published in IEEE Transactions on Automation Science and Engineering (T-ASE).