Zhedong Lin

About Me

Research overview

Hi, I’m Zhedong Lin (林哲栋), an MSc student in Artificial Intelligence at the University of Auckland. I received my undergraduate degree in Computer Science and Technology from Southwest University in 2025. I am currently working under the guidance of Prof. Jiamou Liu, and my research focuses on LLMs, multimodal generative AI, and applications such as text-to-image systems, text-to-video generation, image and video editing, and controllable diffusion models. I will soon begin my PhD studies at the University of Auckland, continuing under the supervision of Prof. Jiamou Liu. If you are interested in my research or would like to discuss potential collaboration, feel free to contact me at zlin629@aucklanduni.ac.nz.

Research Interests

My research focuses on multimodal generative AI, with particular interests in text-to-image and text-to-video generation, image and video editing, controllable diffusion models, and LLMs. I am interested in developing foundation-model-based methods that generate coherent, high-quality, and controllable visual content across different modalities.

  • Text-to-Image and Text-to-Video Generation: Generating high-quality visual content from textual descriptions with better consistency and semantic alignment.
  • Image and Video Editing: Enabling flexible, user-guided editing while preserving contextual and visual coherence.
  • Controllable Diffusion Models: Improving fine-grained control over generative processes for creative and practical applications.
  • Multimodal Foundation Models: Exploring how LLMs and multimodal models can support generation, editing, and cross-modal understanding.

My work aims to advance AI systems for creating consistent, controllable, and editable visual content.

News and Updates

Selected Publications

📄 Narratology Meets Text-to-Image: A Survey of Consistency in AI Generated Storybook Illustrations
Zhedong Lin, Zhongsheng Wang, Qian Liu, Xinyu Zhang, Jiamou Liu
Artificial Intelligence Review (JCR Q1, SCI Q1 Top), 2026
Paper

📄 CharCom: Composable Identity Control for Multi-Character Story Illustration
Zhongsheng Wang, Ming Lin, Zhedong Lin, Yaser Shakib, Qian Liu, Jiamou Liu
ACM Multimedia Asia 2025 (CCF-C, Best Multimedia Award)
Paper


Projects

🚀 Code Vibe Reading — VS Code extension for AI-assisted code understanding and navigation
Project

Awards & Honors

  • China Scholarship Council (CSC) Full Scholarship
  • University of Auckland High Achiever Scholarship
  • University of Auckland First in Course Award
  • Outstanding Graduate at Southwest University
  • Best Multimedia AwardACM Multimedia Asia 2025

Teaching

  • Teaching Assistant, COMPSCI 120: Mathematics for Computer Science