Dec 2025 - Sept 2026
Collaboration Intern with Yunfei Liu
Shenzhen, China
About Me
I am a first-year Master's student at HCP Lab, Sun Yat-sen University, advised by Prof. Guanbin Li. I received my B.E. from the School of Artificial Intelligence, Xidian University. Previously, I was a visiting student at CLR Lab, Westlake University, working with Prof. Yandong Wen on LLMs mathematical reasoning, and interned at Huawei IAS BU, working with Yunfei Liu on driving video synthesis. I also closely collaborate with Chengzhuo Tong and Bohan Zeng from DCAI Group, Peking University, on video world models.
My current work focuses on Video Generation & World Models, with a special interest in real-time interactive and game-oriented video world models.
I am always happy to exchange ideas, learn from feedback, and explore possible collaborations with people in and beyond the field, feel free to reach out by email or WeChat!
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "News
Jun 18
Graduated from Xidian University 🎓
May 1
CoF-T2I was accepted by ICML 2026 🎉
Apr 6
OpenWorldLib technical report released 🎉
Dec 1
Began my internship at Huawei ADS BU 🚗
Publications (view all ) * Equal Contribution † Corresponding Author
RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models
Yuwei Ning, Liangzhi Wang, Yi Xiao, Zhenhua Wu, Yun Pang, Mingkun Chang, Jichang Li, Guanbin Li†
arXiv preprint 2026
RealWeather learns realistic and scene-faithful weather translation for driving videos from real-world weather dynamics, improving visual realism while preserving safety-critical scene structure.
RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models
Yuwei Ning, Liangzhi Wang, Yi Xiao, Zhenhua Wu, Yun Pang, Mingkun Chang, Jichang Li, Guanbin Li†
arXiv preprint 2026
RealWeather learns realistic and scene-faithful weather translation for driving videos from real-world weather dynamics, improving visual realism while preserving safety-critical scene structure.
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Zhenhua Wu*, Yun Pang*, Mingkun Chang*, Yuwei Ning, Liangzhi Wang, Yi Xiao, Guanbin Li†
arXiv preprint 2026
RealityBridge is a structure-preserving and asset-aware Sim-to-Real framework for improving edited 3DGS driving videos, targeting artifact removal, realism, and temporal consistency.
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
Zhenhua Wu*, Yun Pang*, Mingkun Chang*, Yuwei Ning, Liangzhi Wang, Yi Xiao, Guanbin Li†
arXiv preprint 2026
RealityBridge is a structure-preserving and asset-aware Sim-to-Real framework for improving edited 3DGS driving videos, targeting artifact removal, realism, and temporal consistency.
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
Chengzhuo Tong*, Mingkun Chang*, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Ruichuan An, Bohan Zeng, Yang Shi, Yifan Dai, Ziming Zhao, Guanbin Li, Pengfei Wan, Yuanxing Zhang, Wentao Zhang†
ICML 2026
[TL;DR] [Paper] [Project] [Code]
CoF-T2I studies how video models can perform frame-by-frame visual reasoning for text-to-image generation, using intermediate frames as explicit reasoning steps toward the final image.
CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation
Chengzhuo Tong*, Mingkun Chang*, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Ruichuan An, Bohan Zeng, Yang Shi, Yifan Dai, Ziming Zhao, Guanbin Li, Pengfei Wan, Yuanxing Zhang, Wentao Zhang†
ICML 2026
[TL;DR] [Paper] [Project] [Code]
CoF-T2I studies how video models can perform frame-by-frame visual reasoning for text-to-image generation, using intermediate frames as explicit reasoning steps toward the final image.
Local Concept Learning for Personalized Federated Learning
Shuo Li, Mingkun Chang, Pengfang Li, Jiahao Wang, Yang Liu, Mengru Ma
PRCV 2026
Local Concept Learning studies personalized federated learning by modeling local concepts across heterogeneous clients for more adaptive personalization.
Local Concept Learning for Personalized Federated Learning
Shuo Li, Mingkun Chang, Pengfang Li, Jiahao Wang, Yang Liu, Mengru Ma
PRCV 2026
Local Concept Learning studies personalized federated learning by modeling local concepts across heterogeneous clients for more adaptive personalization.
Projects (view all )
OpenWorldLib
Core Contributor · 2026 · 828 stars
World Models, Multimodal Generation, Unified Inference Framework
[TL;DR] [GitHub] [Tech Report]
A unified open-source codebase for advanced world models, integrating perception-centered world-model methods across visual generation, reasoning, VLA, and simulation-related tasks.
OpenWorldLib
Core Contributor · 2026 · 828 stars
World Models, Multimodal Generation, Unified Inference Framework
[TL;DR] [GitHub] [Tech Report]
A unified open-source codebase for advanced world models, integrating perception-centered world-model methods across visual generation, reasoning, VLA, and simulation-related tasks.
Experience
CLR Lab, Westlake University
Mar 2025 - Sept 2025
Visiting Student with Prof. Yandong Wen
Hangzhou, China
Education
Sun Yat-sen University
Sept 2026 - June 2029
M.E. in Computer Science and Engineering
Guangzhou, China
Xidian University
Sept 2022 - June 2026
B.E. in Artificial Intelligence
GPA: 90.3/100, Rank: 7/129
GPA: 90.3/100, Rank: 7/129
Xi'an, China
Awards
- First-Class Academic Scholarship, Sun Yat-sen University 2026
- Second-Class Academic Scholarship, Xidian University 2023&2024&2025
- Meritorious Winner in Mathematical Contest in Modeling (MCM/ICM, Top 7.23% of 10,388 teams) 2024
- Provincial Second Prize, National College Student Mathematics Competition 2023