Zhongsheng Wang

Zhongsheng Wang

PhD Student

University of Auckland

Research Interests

MLLM
AIGC
Self-Evolving AI Agent
Multi-agent System

Hobbies

Photography
Delicacy
Online games: Arknights, Valorant

About

I am a PhD Candidate in CS in the School of Computer Science, University of Auckland, supervised by Prof. Jiamou Liu (刘佳谋) and Dr. Qian Liu (刘茜).

Before that, I received my undergraduate degree in Computer Science and Technology at the School of Computer Science and Technology, School of Software, Southwest University in 2023 and master degree in Data Science at the School of Computer Science, University of Auckland in 2024.

My current research interests lie in AIGC (especially the consistency and continuity of Text-to-Image generation), and the Self-Evolution of AI Agents. If you are interested in collaboration, please contact me by email.

Apart from scientific research, I prefer photography, exploring cuisine, and playing games in my leisure time! For some landscape/cultural photos, please visit Gallery.

Selected Publications

View All

SDO: Subspace Deconflicting Operator for Multi-Adapter Composition

Zhongsheng Wang, Zhedong Lin, Qian Liu, Xinyu Zhang, Jiamou Liu

Proceedings of the 34th ACM International Conference on Multimedia

Introduces SDO, a parameter-space operator for reducing interference when composing multiple independently trained adapters in diffusion models, improving identity fidelity and compositional stability in multi-character generation.

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

Provides a comprehensive survey that grounds AI‑generated storybook illustration in narratology, defining six dimensions of consistency and reviewing methods, datasets, metrics and challenges across time, space, character, plot, style and theme.

CharCom: Composable Identity Control for Multi-Character Story Illustration

Zhongsheng Wang, Ming Lin, Zhedong Lin, Yaser Shakib, Qian Liu, Jiamou Liu

Proceedings of the 7th ACM International Conference on Multimedia in Asia

2026-08

🎉 One papers was accepted by EMNLP 2026!

2026-07

🎉 Two papers was accepted by ACM MM 2026 (1st author and 1st co-author), thanks to all contributors!

2026-05

🎉 R-Debater (published on AAMAS 2026) has won the Best Paper Award.

2026-04

🎉 I just finished my oral presentation in provisional year review. Formally become a PhD candidate!

2026-01

🎉 One paper was accepted by Artificial Intelligence Review (2nd author), thanks to all contributors!

2025-12

🎉 Our paper presented in ACM Multimedia Aisa has won the Best Multimedia Award!