Hi, I’m Jiwen, a researcher and frontier explorer in generative AI.
I’m building Video World Model: AI systems that generate consistent, controllable video environments with real-time interactivity, memory, and reasoning capabilities. As Genie 3 and Project Genie have shown, this is the foundation for next-generation simulation, robotics, and interactive media, yet there’s still a long way to go.
🤗 I’m fortunate to have Yiran Qin as a close friend and collaborator. We share a deep interest in the intersection of world models and robotics.
🚀 In 2026, I’m working toward releasing this technology as several open-source projects.
🤝 Open to collaborations from academia, industry, or investment. If you’re interested in video world models, let’s talk!
Contact me via 📬 Email / WeChat
Research Vision
My long-term research goal is to build ideal Video World Model. I’m currently focused on three core challenges:
Selected Publications
(*: indicates equal contribution; #: indicates corresponding author)
Research Topics: World Model / Interactive Video Generation / Embodied AI
Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
Jiwen Yu, Jianhong Bai, Yiran Qin, Quande Liu#, Xintao Wang, Pengfei Wan, Di Zhang, Xihui Liu#
SIGGRAPH Asia 2025
Paper | Project Page | Dataset
GameFactory: Creating New Games with Generative Interactive Videos
Jiwen Yu*, Yiran Qin*, Xintao Wang#, Pengfei Wan, Di Zhang, Xihui Liu#
ICCV 2025 Highlight
Paper | Project Page | GitHub | Dataset
Survey of Interactive Generative Video
Jiwen Yu*, Yiran Qin*, Haoxuan Che*, Quande Liu#, Xintao Wang, Pengfei Wan, Di Zhang, Kun Gai, Hao Chen, Xihui Liu#
Position: Interactive Generative Video as Next-Generation Game Engine
Jiwen Yu*, Yiran Qin*, Haoxuan Che, Quande Liu, Xintao Wang#, Pengfei Wan, Di Zhang, Xihui Liu#
WorldSimBench: Towards Video Generation Models as World Simulators
Yiran Qin*, Zhelun Shi*, Jiwen Yu, Xijun Wang, Enshen Zhou, Lijun Li, Zhenfei Yin, Xihui Liu, Lu Sheng, Jing Shao, Lei Bai, Wanli Ouyang, Ruimao Zhang
ICML 2025
SkillMimic: Learning Reusable Basketball Skills from Demonstrations
Yinhuai Wang*, Qihan Zhao*, Runyi Yu*, Ailing Zeng, Jing Lin, Zhengyi Luo, Hok Wai Tsui, Jiwen Yu, Xiu Li, Qifeng Chen, Jian Zhang, Lei Zhang, Ping Tan
CVPR 2025 Highlight
Paper | Project Page | GitHub
Past Research Topic: Training-free Applications of Diffusion Model
My research journey began during my Master’s studies, coinciding with the paradigm shift brought by diffusion models in generative AI (2021-2023). This revolutionary advancement inspired my initial research on zero-shot applications of diffusion models, spanning multiple domains including image restoration, generation, editing, steganography, and video synthesis.
AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
Jiwen Yu, Xiaodong Cun#, Chenyang Qi, Yong Zhang, Xintao Wang, Ying Shan, Jian Zhang#
Project 2023
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Yinhuai Wang*, Jiwen Yu*, Jian Zhang#
ICLR 2023 Spotlight
Paper | GitHub | Project Page
Educations
Internships
2024.09 - 2026.01
Student Researcher (Kuai Star) at Kling team, Shenzhen, China
Advisor: Dr. Xintao Wang
Talks
- Dec 2025 Controllable, Generalizable, and Memory-Enabled: Interactive Video World Models
- SAAI. [News Report] (Chinese)
- Dec 2025 Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval
- GAMES. [Video] (Chinese)
- Oct 2025 Toward Higher-Level Intelligence in Interactive Generative Video for World Model
- AITIME. [Video] (Chinese)
- Jul 2025 Toward Higher-Level Intelligence of Interactive Generative Video
- TechBeat. [Video] (Chinese)
Academic Service
- Primary Organizer, VideoWorldModel (CVPR’26 Workshop)
- Reviewer, ICLR, NeurIPS, ICML, ECCV, CVPR, ICCV, SIGGRAPH, SIGGRAPH Asia, TPAMI.