Text-to-Image & Video
Generating high-quality visual content with stronger semantic alignment and cross-frame consistency.
Multimodal Generative AI · LLMs
Zhedong Lin
林哲栋
Hi, I’m Zhedong Lin (林哲栋). I am currently preparing to begin my PhD studies at the University of Auckland, where I will continue my research under the supervision of Prof. Jiamou Liu and Prof. Xinyu Zhang. I hold an MSc in Artificial Intelligence from the University of Auckland and received my BSc in Computer Science and Technology from Southwest University in 2025. My research interests include large language models (LLMs), multimodal generative AI, and their applications in text-to-image synthesis, text-to-video generation, image and video editing, and controllable diffusion models. If you are interested in my research or would like to discuss potential collaborations, please feel free to contact me at zlin629@aucklanduni.ac.nz.
AffiliationUniversity of Auckland
ResearchGenerative AI & multimodal foundation models
Based inChina / New Zealand
Research interests
Image & Video Editing
Enabling flexible, user-guided editing while preserving context, identity, and visual coherence.
Controllable Diffusion
Improving fine-grained control over generative processes for creative and practical applications.
Multimodal Foundation Models
Studying how LLMs and multimodal models support generation, editing, and cross-modal understanding.
News & updates
- 🎉 One paper was accepted by ACM Multimedia 2026 (ACM MM 2026) (CCF-A).
- 🎤 Delivered a guest lecture on Agentic AI at WHMC.
- 🚀 Contributed to the open-source project Code Vibe Reading, a VS Code extension for AI-assisted code understanding and navigation.
- 🎉 One paper was accepted by Artificial Intelligence Review (SCI Q1 Top).
- 🎉 Won the Best Multimedia Award at ACM MM Asia 2025.
- 🎓 Received the China Scholarship Council (CSC) Full Scholarship for PhD studies at the University of Auckland, starting in 2026.
- 🎉 One paper was accepted by ACM MM Asia 2025 (CCF-C).
- 🎓 Graduated with a BSc in Computer Science and Technology from Southwest University and received the Outstanding Graduate honor.
Selected publications
View all publications →SDO: Subspace Deconflicting Operator for Multi-Adapter Composition
Zhongsheng Wang, Zhedong Lin, Qian Liu, Xinyu Zhang, Jiamou Liu
ACM Multimedia 2026 · CCF-A
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
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
Explore
Education
My academic path from Southwest University to postgraduate research at the University of Auckland.
Academic background →Teaching
Teaching assistance in advanced machine learning and mathematics for computer science, plus a guest lecture on Agentic AI.
Teaching experience →Honors & Awards
Research, scholarship, course, and graduation distinctions across my academic journey.
View honors →Open source
Code Vibe Reading is a VS Code extension for AI-assisted code understanding and navigation.
View project →