Yu Shang 商宇

I am a researcher at Tongyi Lab (Wan Team) , Alibaba Group. Before that, I received my Ph.D. and B.E. degrees in the Department of Electronic Engineering from Tsinghua University, and a second B.E. degree from the School of Economics and Management at Tsinghua University.

My current research focuses on video understanding, video generation and world model.

Yu Shang

Project

Wan 3.0
Wan3.0
Wan Team
An all-in-one video generation model with native 30-second storytelling, multi-modal omni-reference, cinematic realism, and synchronized audio.
WorldArena overview WorldArena
WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
AI Open
Yu Shang (Project Lead), Zhuohang Li, Yiding Ma, Weikang Su, Xin Jin, Ziyou Wang, Lei Jin, Xin Zhang, Yinzhou Tang, Haisheng Su, Chen Gao, Wei Wu, Xihui Liu, Dhruv Shah, Zhaoxiang Zhang, Zhibo Chen, Jun Zhu, Yonghong Tian, Tat-Seng Chua, Wenwu Zhu, Yong Li
paper project page code leaderboard competition 中文报道1 中文报道2
A unified benchmark for embodied world models, evaluating both perceptual quality and functional utility.
WorldArena 2.0 overview WorldArena 2.0
WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
Preprint 2026
Yu Shang (Project Lead), Yinzhou Tang, Yiding Ma, Zhuohang Li, Lei Jin, Weikang Su, Xin Jin, Zhaolu Wang, Ziyou Wang, Xin Zhang, Haisheng Su, Weizhen He, Wei Wu, Haoyi Duan, Gordon Wetzstein, Xihui Liu, Dhruv Shah, Zhaoxiang Zhang, Zhibo Chen, Jun Zhu, Yonghong Tian, Tat-Seng Chua, Wenwu Zhu, Chen Gao, Yong Li
paper project page code leaderboard competition
An expanded benchmark across modality, functionality, and platform for embodied world model evaluation.
RoboScape framework RoboScape
RoboScape: Physics-informed Embodied World Model
Spotlight NeurIPS 2025 CCF-A
Yu Shang, Xin Zhang, Yinzhou Tang, Lei Jin, Chen Gao, Wei Wu, Yong Li
paper 中文报道
A physics-informed embodied world model with temporal depth prediction and adaptive keypoint dynamics.
AgentSquare framework AgentSquare
AgentSquare: Automatic LLM Agent Search in Modular Design Space
ICLR 2025 CCF-A
Yu Shang*, Yu Li*, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, Yong Li
paper code project page 中文报道
Automatic search of LLM agents in a modular design space.
AgentRecBench overview AgentRecBench
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
Spotlight NeurIPS 2025 CCF-A
Yu Shang, Peijie Liu, Yuwei Yan, Zijing Wu, Leheng Sheng, Yuanqing Yu, Chumeng Jiang, An Zhang, Fengli Xu, Yu Wang, Min Zhang, Yong Li
paper dataset & benchmark
A benchmark for LLM-agent-based personalized recommender systems.

News

Selected / First-author Publications

WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
AI Open
Yu Shang, Zhuohang Li, Yiding Ma, Weikang Su, Xin Jin, Ziyou Wang, Lei Jin, Xin Zhang, Yinzhou Tang, Haisheng Su, Chen Gao, Wei Wu, Xihui Liu, Dhruv Shah, Zhaoxiang Zhang, Zhibo Chen, Jun Zhu, Yonghong Tian, Tat-Seng Chua, Wenwu Zhu, Yong Li
paper
RoboScape: Physics-informed Embodied World Model
Spotlight NeurIPS 2025 CCF-A
Yu Shang, Xin Zhang, Yinzhou Tang, Lei Jin, Chen Gao, Wei Wu, Yong Li
paper
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
Spotlight NeurIPS 2025 CCF-A
Yu Shang, Peijie Liu, Yuwei Yan, Zijing Wu, Leheng Sheng, Yuanqing Yu, Chumeng Jiang, An Zhang, Fengli Xu, Yu Wang, Min Zhang, Yong Li
paper dataset & benchmark
AgentSquare: Automatic LLM Agent Search in Modular Design Space
ICLR 2025 CCF-A
Yu Shang*, Yu Li*, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, Yong Li
paper code page
A Large-scale Dataset with Behavior, Attributes, and Content of Mobile Short-video Platform
WWW 2025 CCF-A
Yu Shang, Chen Gao, Nian Li, Yong Li
paper dataset & code
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms
WWW 2025 CCF-A
Yuwei Yan*, Yu Shang*, Qingbin Zeng, Yu Li, Keyu Zhao, Zhiheng Zheng, Xuefei Ning, Tianji Wu, Shengen Yan, Yu Wang, Fengli Xu, Yong Li
paper code page
Improving Item-side Fairness of Multimodal Recommendation via Modality Debiasing
WWW 2024 CCF-A
Yu Shang, Chen Gao, Jiansheng Chen, Depeng Jin, Yong Li
paper
Enhancing Adversarial Robustness of Multi-modal Recommendation via Modality Balancing
ACM MM 2023 CCF-A
Yu Shang, Chen Gao, Jiansheng Chen, Depeng Jin, Huimin Ma, Yong Li
paper
Learning Fine-grained User Interests for Micro-video Recommendation
SIGIR 2023 CCF-A
Yu Shang, Chen Gao, Jiansheng Chen, Depeng Jin, Meng Wang, Yong Li
paper
Transferable Structure-based Adversarial Attack of Heterogeneous Graph Neural Network
CIKM 2023 CCF-B
Yu Shang, Yudong Zhang, Jiansheng Chen, Depeng Jin, Yong Li
paper
RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
CVPR 2026 CCF-A
Yinzhou Tang*, Yu Shang*, Yinuo Chen*, Bingwen Wei, Xin Zhang, Shu'ang Yu, Liangzhi Shi, Chao Yu, Chen Gao, Wei Wu, Yong Li
paper
UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding
ICML 2026 CCF-A
Xin Zhang*, Tianjian Ouyang*, Yu Shang*, Qingmin Liao, Yong Li
paper

* indicates co-first authors.

Honors & Awards

Academic Service