Tianyi Yan

IOTSC, University of Macau · Macau / Beijing

I am a Ph.D. student at the State Key Laboratory of Internet of Things for Smart City (SKL-IOTSC), University of Macau, advised by Prof. Jianbing Shen and Prof. Chengzhong Xu. Previously, I obtained my Master's degree from the Institute of Automation, Chinese Academy of Sciences (CASIA), working with Prof. Jinqiao Wang and Prof. Ming Tang, and my B.Eng. degree from BUPT, working with Prof. Chuan Shi. I have also gained industrial experience at Alibaba Qwen, Xiaomi EV, and Li Auto as a research intern.

My research lies at the intersection of Generative World Models, End-to-End Autonomous Driving, Embodied AI, and LLM Post-Training / Evaluation. Currently, my primary focus is on enabling agents to achieve infinite driving and self-play within physically reliable, imaginative world models, as well as advancing LLM evaluation and post-training methodologies.

Email Scholar GitHub

News

2026.02 Two papers WorldLens and AD-R1 are accepted by CVPR 2026! See u in DENVER!
2025.09 One paper RLGF is accepted by NeurIPS 2025! See u in SAN DIEGO!
2025.07 One paper is accepted by ACM MM 2025!
2025.06 One paper is accepted by ICCV 2025!
2025.02 One paper DrivingSphere is accepted by CVPR 2025! See u in NASHVILLE!

Publications

Selected Preprints

OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space

Zhuding Liang*, Tianyi Yan*, Dubing Chen, Jiasen Zheng, Huan Zheng, et al.

arXiv 2026

Paper

CausalDrive: Real-time Causal World Models for Autonomous Driving

Tianyi Yan, Huan Zheng, Dubing Chen, Meizhi Qu, et al.

arXiv 2026

Paper

From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous Driving

Huan Zheng*, Yucheng Zhou*, Tianyi Yan*, Jiayi Su, Hongjun Chen, Dubing Chen, et al.

arXiv 2026

Paper

3D and 4D World Modeling: A Survey

Lingdong Kong, Wesley Yang, Jianbiao Mei, Youquan Liu, Ao Liang, Dekai Zhu, et al.

arXiv 2025

Paper

Selected Papers

WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

Ao Liang*, Lingdong Kong*, Tianyi Yan*, Hongsi Liu*, Wesley Yang*, Ziqi Huang, Wei Yin, et al.

CVPR 2026, oral

Paper Code

AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models

Tianyi Yan, Tao Tang, Xingtai Gui, Yongkang Li, Jiasen Zheng, Weiyao Huang, Lingdong Kong, et al.

CVPR 2026, findings

Paper

RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation

Tianyi Yan, Wencheng Han, Xia Zhou, Xueyang Zhang, Kun Zhan, Cheng-zhong Xu, Jianbing Shen

NeurIPS 2025

Paper

DrivingSphere: Building a High-fidelity 4D World for Closed-loop Simulation

Tianyi Yan, Dongming Wu, Wencheng Han, Junpeng Jiang, Xia Zhou, Kun Zhan, Cheng-zhong Xu, Jianbing Shen

CVPR 2025

Paper

OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving

Tianyi Yan*, Junbo Yin*, Xianpeng Lang, Ruigang Yang, Cheng-Zhong Xu, Jianbing Shen

AAAI 2025

Paper

Experience

Education

Ph.D. Student

University of Macau — SKL-IOTSC

Advisors: Prof. Jianbing Shen, Prof. Chengzhong Xu

2023 – Present

M.S. in Pattern Recognition

Institute of Automation, Chinese Academy of Sciences

Advisors: Prof. Jinqiao Wang, Prof. Ming Tang

2020 – 2023

B.Eng. in Computer Science

Beijing University of Posts and Telecommunications

Advisor: Prof. Chuan Shi

2016 – 2020

Industrial Experience

Research Intern

Alibaba Group — Tongyi Lab (Qwen)

Physical AI · World Models · LLM Evaluation

2026.3 – Present

Research Intern

Xiaomi EV

Autonomous Driving · World Models

2025.12 – 2026.3

Research Intern

Li Auto

Autonomous Driving · Generative Models

2023 – 2025.11