Visual synthesis
Text-to-image and text-to-video generation with better consistency and semantic alignment.
Academic background
Education
My academic path brings together computer science, artificial intelligence, and multimodal generative research.
- Current
PhD · University of Auckland
Supervisors: Prof. Jiamou Liu and Prof. Xinyu Zhang
Research in multimodal generative AI, controllable visual generation, and foundation models.
- 2026
MSc · Artificial Intelligence
University of Auckland · Auckland, New Zealand
Postgraduate study in artificial intelligence with a focus on multimodal and generative learning.
- 2025
BSc · Computer Science and Technology
Southwest University · Chongqing, China
Graduated with the Outstanding Graduate honor.
Research focus
Controllable models
Fine-grained control for practical and creative generative workflows.
Image & video editing
User-guided editing that preserves identity, context, and coherence.
Multimodal AI
LLMs and foundation models for cross-modal understanding and generation.