Zihao Zhang

Zihao Zhang (张子豪)

I am a third-year Ph.D. student at Southeast University and Shenzhen Loop Area Institution (SLAI). My tutor in Southeast University is Prof. Ziyuan Pu. In SLAI first year, I am supervised by Prof. Hongyang Li. And now I am supervised by Prof. Ping Luo.

Prior to joining Southeast University, I earned my M.S. (2024) in Transportation from Hunan University, supervised by Prof. Chenhui Liu.

My research focuses on autonomous driving and Embodied AI, particularly End-to-End Autonomous Driving, 3D object detection, trajectory prediction, and driving behavior analysis.

News

October 10, 2026: We released our paper "SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models" at arxiv.
October 7, 2026: We released our paper "Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?" at arxiv.
July, 2025: Our paper "Roadside Monocular 3D Detection via Cross-View Semantic Alignment" was accepted by ITSC 2025.
April, 2025: My project on federated learning for collaborative perception was sponsored by Jiangsu Province.
September, 2024: Two papers recommended to present at TRB Annual Meeting.

Publications

Autonomous Driving

	Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving? Zihao Zhang, Haochen Tian, Tianyu Li, Changhui Jing, Jingliang He, Naisheng Ye, Ziyuan Pu, and Zhenjie Yang. preprint, 2026
	Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models Changhui Jing, Haochen Tian, Hongchen Li, Tianyu Li, Caojun Wang, Zihao Zhang, Yanhao Liu, Chengen Xie, Bailin Li, Hao Zhao, and Zhenjie Yang. preprint, 2026
	Roadside Monocular 3D Detection via Cross-View Semantic Alignment Pei Liu, Zihao Zhang, Haipeng Liu, Yiqun Li, Junlan Chen, Ziyuan Pu. Transportation Research Board (TRB) / IEEE ITSC, 2025
	Risk-Informed Diffusion Transformer for Long-Tail Trajectory Prediction in the Crash Scenario Junlan Chen, Pei Liu, Zihao Zhang, Hongyi Zhao, Ziyuan Pu. Transportation Research Board (TRB), 2025

Traffic Agent Behavior Analysis

	Optimizing charging station locations for mixed traffic of electric and gasoline vehicles: a stochastic user equilibrium approach Bing Zeng, Xinlian Yu, Zihao Zhang, Ziyuan Pu. Transportation Research Part E: Logistics and Transportation Review, 2025
	Identification of the factors influencing speeding behaviour of food delivery e-bikers in China with the naturalistic cycling data Zihao Zhang and Chenhui Liu. International Journal of Occupational Safety and Ergonomics, 2025
	Exploration of the Characteristics of Elderly-Driver-Involved Single-Vehicle Hit-Fixed-Object Crashes in Pennsylvania, USA Xuerui Hou, Zihao Zhang, Xue Su, Chenhui Liu. Applied Sciences, 2025
	Exploration of the Heterogeneity among Elderly Drivers by Analyzing Traffic Crash Data: A Case Study in Pennsylvania, USA Zihao Zhang and Chenhui Liu. SAE International, 2024
	Exploration of Riding Behaviors of Food Delivery Riders: A Naturalistic Cycling Study in Changsha, China Zihao Zhang and Chenhui Liu. Sustainability, 2023
	Why the Elderly Do Not Travel: An Analysis Based on the 2017 NHTS Data Zihao Zhang and Chenhui Liu. CICTP, 2023

Research

My research interests span several areas in Embodied AI and Autonomous Driving:

World Action Models: 3D or 4D world action models for autonomous driving or embodied AI.
Deep Reinforcement Learning: Post-training methods that learn safety boundaries for physical AI.
Agent Harness for Physical World: Adapting coding-agent harnesses to physical tasks such as driving and manipulation.

Design and source code from Jon Barron's website
Last updated: October 2026