Hi, I’m Jiwen. I am a first-year Ph.D. student at The University of Hong Kong (HKU), supervised by Prof. Xihui Liu. Currently, I also work as a research intern at Kuaishou Technology under the guidance of Dr. Xintao Wang, working closely with my friend Yiran Qin. Prior to this, I received my Master’s degree from Peking University, where I was supervised by Prof. Jian Zhang. My research interests cover generative models and embodied AI, with a particular focus on physical and virtual applications of video generation models.

I am always open to academic and industrial collaborations. My specific research interests include:

Development of foundational video generation models (autoregressive models, causal inference, and efficient architectures)
Video generation models as world simulators (generalization, physics-compliance, memory consistency, and causal reasoning)
Multi-agent embodied AI

Feel free to reach out for research discussions and potential collaborations!

Selected Publications

(*: indicates equal contribution; #: indicates corresponding author)

Current Research Topics: Video Generation Model / World Model / Embodied AI

Video generation models learn world knowledge from large-scale video data, showing promise in simulating the physical world and even synthesizing novel virtual worlds. I envision video generation models evolving into comprehensive world simulators, with applications spanning gaming, embodied AI, and beyond.

Preprint

GameFactory: Creating New Games with Generative Interactive Videos

Jiwen Yu^*, Yiran Qin^*, Xintao Wang^#, Pengfei Wan, Di Zhang, Xihui Liu^#

Preprint, 2025

Paper | Project Page | GitHub | Dataset

Preprint

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^#

Preprint, 2025

Paper

Preprint

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

Preprint, 2024

Paper | Project Page

CVPR 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

Paper | Project Page | GitHub

Early 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.

Project