I am currently an M.Phil. student in the AI Thrust at 
HKUST(GZ). My supervisor is Prof. Yingcong Chen, a super nice mentor.
Before that, I received my Bachelor’s degree in Computer Science and Technology from the School of Computer Science and Technology, 
Harbin Institute of Technology, under the supervision of Prof. Shaohui Liu, who has been tremendously supportive.
At present, I am working closely with Luozhou Wang and Guibao Shen, both of whom are very kind and supportive. My current research focuses on controllable video generation and interactive world model, and I aim to make rapid progress and contributions in these areas.
😍😍😍Please feel free to contact with me via duyihua0130@gmail.com😍😍😍
🔥 News
- 2026.09: ❤️ We released SolarWM and ReWorld, great works.
- 2026.02: 🎉 Our Video-World-Models survey was reported by JiQiZhiXin.
- 2026.01: ❤️ Joined LIGHTSPEED STUDIOS,
as a Researcher.
- 2025.12: 🎉 StereoPilot was reported by JiQiZhiXin.
- 2025.12: 🏎️ See you at the 2026 Formula 1 Chinese Grand Prix in Shanghai!!!
📑 Technical Reports
SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models
Junchao Huang, Guian Fang, Shengju Qian, Xianghao Kong, Zhuoran Zhao, Wei Huang, Yihua Du, Zixin Zhang, Justin Cui, Yuchao Gu, Yukang Chen, Xinting Hu, Tianyu He, Shaoshuai Shi, Zhuotao Tian, Xin Wang, Mike Zheng Shou, Li Jiang
Project Page | Code | 🤗 Dataset | 🤗 Models | arXiv
- SolarWM provides an open foundation spanning 1.43 million clips from 10 source datasets and a unified three-stage training recipe across four 5B–33B video backbones, enabling real-time interactive rollouts from minutes to hours after training only on 5-second clips.
📝 Publications
*denotes equal contribution, † denotes corresponding author
ReWorld: An Interactive World Model with Long-Horizon Memory
Zhifei Chen*, Luozhou Wang*, Guibao Shen, Dongyu Yan, Shuai Yang, Tianshuo Xu, Yihua Du, Wei Wang, Tianyi Gui, Lianghua Huang, Ying-Cong Chen†
Project Page | Code | 🤗 Daily Paper | arXiv
- ReWorld decouples short-horizon action control from long-horizon memory and combines a fixed-budget KV cache with a pose-indexed landmark bank, enabling real-time 704×1280 interactive video streaming with consistent recall of revisited scenes.
StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors
Guibao Shen*, Yihua Du*, Wenhang Ge*, Jing He, Chirui Chang, Donghao Zhou, Zhen Yang, Luozhou Wang, Xin Tao, Ying-Cong Chen†
Project Page | Code | 🤗 Daily Paper | 📰 机器之心 | arXiv
- Converting a 5-second monocular video into a stereoscopic video takes only 11 seconds. Built both parallel and converged 3D dataset.
VideoMemory: Toward Consistent Video Generation via Memory Integration
Jinsong Zhou*, Yihua Du*, Xinli Xu*, Luozhou Wang, Zijie Zhuang, Yehang Zhang, Shuaibo Li, Xiaojun Hu, Bolan Su, Ying-Cong Chen†
Project Page | Code | arXiv
- Propose an entity-centric, dynamic memory bank framework that enables coherent long-form, multi-shot narrative video generation by retrieving and updating character/prop/background states to preserve identity across temporal gaps.
A Mechanistic View on Video Generation as World Models: State and Dynamics
Luozhou Wang*, Zhifei Chen*, Yihua Du, Dongyu Yan, Wenhang Ge, Guibao Shen, Xinli Xu, Leyi Wu, Man Chen, Tianshuo Xu, Peiran Ren, Xin Tao, Pengfei Wan, Ying-Cong Chen†
Code | 🤗 Daily Paper | arXiv | 📰 机器之心
- Bridge this divide: (1) Taxonomy: Unifying Implicit Context vs. Explicit Latent Compression (2) Evolution: Shifting benchmarks from “Visual Fidelity” to “Physical Persistence” and Causality.
Liveness detection method based on multi-angle forensics
Yihua Du, Puchao Zhou, Yu Li, Shaohui Liu
- This work is completed under the guidance of my undergraduate graduation supervisor and the laboratory senior.
- Won the excellent innovation comprehensive graduation design
📖 Educations
- 2021.08 - 2025.09, Bachelor, Harbin Institute of Technology, Harbin.
- 2023.07 - 2023.08,
Summer Camp student(Workshop), National University of Singapore, Singapore. - 2025.09 - (now),
M.Phil., Hong Kong University of Science and Technology (Guangzhou), Guangzhou.
💻 Internships
- 2026.01 - now, Tencent, IEG, Video Generation, Shenzhen.
- 2025.02 - 2025.08, ENVISION Lab, HKUST(GZ), Research Assistant, Guangzhou.
- 2024.03 - 2024.07, Meituan
, Algorithm strategy, Beijing.
📄 My Resume
🎖 Honors and Awards
- 2025.06 Liveness detection method based on multi-angle forensics. Excellent and innovative comprehensive graduation design（卓越创新综合设计奖【哈尔滨工业大学本科生院颁发】）
- 2024.11 HKUST(GZ) RBM Postgraduate Scholarship.
- 2024.11 The Sixth Global Campus Artificial Intelligence Algorithm Elite Competition. The accuracy was second in the whole list and won the second prize in the nation（国家二等奖准确率榜单第二）
- 2024.09 Virtual authoring Communication Community based on Diffusion Model. National Innovation and Entrepreneurship（国家级大创）
- 2022,2023 Excellent student of the school （校优秀学生）
- 2022.09 HIT third-class name Scholarship （三等人民奖学金）
🍭 Habits
- 🏸 Badminton is my absolute favorite! No matter what, I’ll be there if you invite me to play!
- 🎮 I’m also a passionate CS:GO/CS2 enthusiast. Click here to watch my perfect moments!
Last Updated: January 22 2026