Guo Qin

I am a Ph.D. student in Computer Science at The Hong Kong University of Science and Technology, advised by Prof. Dan Xu. My research interests include image and video generation and editing, and interactive world models.

Before joining HKUST, I received my M.S. from Peking University, advised by Prof. Yuesheng Zhu, and my B.Eng. from Xidian University.

News

2026UniGP has been accepted to ECCV 2026.
2026WildActor has been accepted to ICML 2026.
2026IMAGGarment+ has been accepted to AAAI 2026 as an oral presentation.
2025UniMC and Long-Term Talking Face Generation appeared at ICML 2025.
2024Focus on Your Instruction appeared at CVPR 2024.

Publications

UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception

Qin Guo, Hao Luo, Dongxu Yue, Weixuan Jin, Xiao Fu, Fan Wang, Dan Xu

ECCV 2026

A prior-preserved diffusion transformer framework for unified controllable generation, dense perception, and joint RGB-depth-normal generation.

WildActor: Unconstrained Identity-Preserving Video Generation

Qin Guo, Tianyu Yang, Xuanhua He, Fei Shen, Yong Zhang, Zhuoliang Kang, Xiaoming Wei, Dan Xu

ICML 2026

Unconstrained video generation with identity preservation for wild actor settings.

UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation

Qin Guo, Ailing Zeng, Dongxu Yue, Ceyuan Yang, Yang Cao, Hanzhong Guo, Fei Shen, Wei Liu, Xihui Liu, Dan Xu

ICML 2025

A unified diffusion transformer framework for keypoint-guided multi-class image generation.

Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

Qin Guo, Tianwei Lin

CVPR 2024

Fine-grained and multi-instruction image editing by modulating attention according to user instructions.

IMAGGarment+: Efficient Attribute-Wise Diffusion for Garment Generation. Jian Yu, Fei Shen, Cong Wang, Yanpeng Sun, Hao Tang, Qin Guo, Xiaoyu Du. AAAI 2026 Oral.

ChatFace: Chat-Guided Real Face Editing via Diffusion Latent Space Manipulation. Dongxu Yue, Qin Guo, Munan Ning, Jiaxi Cui, Yuesheng Zhu, Li Yuan. arXiv 2023.

AddMe: Zero-shot Group-photo Synthesis by Inserting People into Scenes. Dongxu Yue, Maomao Li, Yunfei Liu, Ailing Zeng, Tianyu Yang, Qin Guo, Yu Li. ECCV 2024.

Long-Term Talking Face Generation via Motion-Prior Conditional Diffusion Model. Fei Shen, Cong Wang, Junyao Gao, Qin Guo, Jisheng Dang, Jinhui Tang, Tat-Seng Chua. ICML 2025.

Open-source Projects

UniGP

Open-AnimateAnyone

DiT-Visualization

Education

2025 - Present Ph.D. student in Computer Science, The Hong Kong University of Science and Technology. Advisor: Prof. Dan Xu.

2022 - 2025 M.S. in Computer Science, Peking University. Advisor: Prof. Yuesheng Zhu.

2018 - 2022 B.Eng. in Information Security, Xidian University.

Experience & Service

2025 - 2026 Research Intern, Meituan.

2024 - 2025 Research Intern, Alibaba DAMO Academy.

2024 Research Intern, Pika Labs.

Service Reviewer for ECCV, NeurIPS, CVPR, ICCV, ICML, and ICLR.