Shuai YANG | Shanghai Jiao Tong University

About Me

I am a third-year Ph.D. student at Shanghai Jiao Tong University & Shanghai AI Laboratory ,co-supervised by Prof. Dahua Lin and Prof. Ziwei Liu. I also works closely with Dr. Tong Wu in Stanford University. Now I am a research intern at the Shanghai Artificial Intelligence Laboratory. My research interests lie in GenAI, and I am currently dedicate to creating open VR interactive world model

Research Interests

Robotics
World Model
3D Vision / Video generation

News

[2025-09] Two papers accepted to NeurIPS 2025.
[2025-06] We release the spmem, a novel method that enhances long-term consistency in video world model via geometry-grounded spatial memory inspired by the human mind.
[2025-04] LayerPano3D accepted to SIGGRAPH 2025.
[2024-12] We release the Imagine360, a novel method that converts standard video into dynamic 360° video with structured motion. .
[2024-08] We release the LayerPano3D, a novel method that generates full-view, explorable panoramic 3D scenes from a single text prompt. .
[2023-09] Start my journey in Shanghai Jiao Tong University.
[2023-08] HyperDreamer accepted to SIGGRAPH Asia 2023.
[2023-06] Graduated from Tongji University.

Publications

Arxiv

PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory
Shuai Yang*, Bingjie Gao*, Ziwei Liu, Jiaqi Wang, Dahua Lin, Tong Wu

Arxiv 2026

Paper Project page Code

NeurIPS

Video World Models with Long-term Spatial Memory
Tong Wu*, Shuai Yang*, Ryan Po, Yinghao Xu, Ziwei Liu, Dahua Lin, Gordon Wetzstein

NeurIPS 2025 (* equal contribution)

Paper Project page Code

NeurIPS

Imagine360: Immersive 360 Video Generation from Perspective Anchor
Jing Tan*, Shuai Yang*, Tong Wu, Jingwen He, Yuwei Guo, Ziwei Liu, Dahua Lin

NeurIPS 2025 (* equal contribution)

Paper Project page Code

SIGGRAPH

LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
Shuai Yang*, Jing Tan*, Mengchen Zhang, Tong Wu, Yixuan Li, Gordon Wetzstein, Ziwei Liu, Dahua Lin

SIGGRAPH, 2025. (* equal contribution)

Paper Project page Code

SIGGRAPH Asia

HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image
Tong Wu*, Zhibing Li*, Shuai Yang*, Pan Zhang, Xingang Pan, Jiaqi Wang, Ziwei Liu, Dahua Lin

SIGGRAPH Asia, 2023. (* equal contribution)

Paper Project page Code

Technical Report

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
Fangzhou Hong, Jiaxiang Tang, Ziang Cao, Min Shi, Tong Wu, Zhaoxi Chen, Shuai Yang , Tengfei Wang, Liang Pan, Dahua Lin, Ziwei Liu
Technical Report

Paper Demo Code

ICASSP

AnimateScene: Camera-controllable Animation in Any Scene
Qingyang Liu*, Bingjie Gao*, Weiheng Huang, Jun Zhang, Zhongqian Sun, Yang Wei, Fengrui Liu, Zelin Peng, Qianli Ma, Shuai Yang, Zhaohe Liao, Haonan Zhao, Li Niu

ICASSP 2026

Paper Project page

Arxiv

RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
Bingjie Gao, Qianli Ma, Xiaoxue Wu, Shuai Yang, Guanzhou Lan, Haonan Zhao, Jiaxuan Chen, Qingyang Liu, Yu Qiao, Xinyuan Chen, Yaohui Wang, Li Niu

Arxiv 2025

Paper Code

Misc

I'm a die-hard NBA fan, and Chicago's own—Derrick Rose—is my all-time favorite. ❤️ The youngest MVP in history! I'm also a big LeBron James fan—you know, the man is a legend!