Shuyao Shang

I'm a second-year Ph.D. student at the NLPR, Institute of Automation, Chinese Academy of Sciences (CASIA) in Beijing, supervised by Prof. Tieniu Tan and Prof. Zhaoxiang Zhang.

My research interests span General World Models and Video Generation Models. I am committed to developing intelligent agents that can autonomously evolve intelligence in open-world exploration, and "Pursuing the Nature of Intelligence" .

$$\text{Knowledge}=\int_{0}^{t}\text{Intelligence}\,\mathrm{d}t$$ $$\text{Intelligence}=\frac{\mathrm{d}}{\mathrm{d}t}\text{Knowledge}.$$

Email / Scholar / Github / Zhihu

Publications

	PhiZero: A World Model Built Around Physical Language Shuyao Shang, Yuqi Wang^†, Ruopeng Gao, Xu Chen, Tieniu Tan, Lue Fan^✉, Zhaoxiang Zhang^✉ Preprint, 2026 A world model that reasons about world evolution in a compact discrete physical language before rendering the inferred transitions into video.
	BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving Bing Zhan^, Shuyao Shang^, Shuo Lu, Yuan Xu, Zhao Wang, Yida Wang, Xueyang Zhang, Kun Zhan, Jiahao Gu^†✉ arXiv, 2026 A brain-inspired action-space coordination framework that unifies semantic priors and predictive dynamics for autonomous-driving planning.
	WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity Yuxue Yang^†, Shuyao Shang^, Jiahe Wang, Zitong Zhou, Liang Tan, Junhan Zeng, Ruizhi Li, Junyan Li, Yu Liu, Xiao Yang, Yong Li, Jun Zhu, Hongsheng Li, Tieniu Tan, Lue Fan^†✉, Zhaoxiang Zhang^✉ arXiv, 2026 A hierarchical diagnostic benchmark with 1,474 test cases across eight tasks, evaluating world models from apparent appearance to inherent reactivity.
	DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving Shuyao Shang^, Bing Zhan^, Yunfei Yan, Yuqi Wang, Yingyan Li, Yasong An, Xiaoman Wang, Jierui Liu, Lu Hou, Lue Fan^✉, Zhaoxiang Zhang^✉, Tieniu Tan ICML, 2026 A Dynamics CoT-based VLA model that reasons over compact future dynamics for autonomous driving.
	DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving Yingyan Li^, Shuyao Shang^, Weisong Liu^, Bing Zhan^, Haochen Wang^, Yuqi Wang, Yuntao Chen, Xiaoman Wang, Yasong An, Chufeng Tang, Lu Hou, Lue Fan^✉, Zhaoxiang Zhang^✉ ICLR, 2026 A world-modeling paradigm amplifying data scalability and improving generalization in autonomous driving.*
	DriveDPO: Policy Learning via Safety DPO for End-to-End Autonomous Driving Shuyao Shang, Yuntao Chen, Yuqi Wang, Yingyan Li, Zhaoxiang Zhang^✉ NeurIPS, 2025 A Safety-DPO policy learning framework that unifies policy distillation and trajectory-level safety preference alignment.
	ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution Shuyao Shang, Zhengyang Shan, Guangxing Liu, Lunqian Wang, Xinghua Wang, Zekai Zhang, Jinglin Zhang^✉ AAAI, 2024 A hybrid approach that guides diffusion in the residual space relative to a CNN prediction to improve high-frequency detail.
	Faster and Lighter Meteorological Satellite Image Classification by a Lightweight Channel-Dilation-Concatenation Net Shuyao Shang, Jinglin Zhang, Xing Wang^✉, Xinghua Wang, Yuanjun Li, Yuanjiang Li IEEE J-STARS, 2023 A Channel-Dilation-Concatenation network structure to reduce parameters and inference time while retaining accuracy.
	CTMU-net: An Improved U-Net for Semantic Segmentation of Remote-Sensing Images with Combined Attention Mechanisms Yuanjun Li, Zhiyu Zhu, Yuanjiang Li, Jinglin Zhang, Xi Li, Shuyao Shang, Dewen Zhu^✉ IEEE J-STARS, 2023 Enhances U-Net for remote-sensing segmentation via combined attention.

Work Experience

ByteDance

Research Intern · General World Models

April 2026 – August 2026

Academic Service

Reviewer: IEEE TPAMI, ICML, NeurIPS, AAAI, and TMLR.

Education

Ph.D. Candidate, Institute of Automation, Chinese Academy of Sciences, Beijing, China (Sept. 2024 – Present).
B.Eng., Shandong University, China (Sept. 2020 – Jun. 2024) (GPA 93.02/100, rank 2/104).

Awards & Achievements

National Scholarship, Shandong University.
Outstanding Graduation Thesis & Outstanding Graduate, Shandong University.