CV

Research Assistant

Dynamic Robot Systems Group, Oxford Robotics Institute (ORI)

3D building layout reconstruction from monocular image sequences.

• Developed SeqLayout3D, a bottom-up system that reconstructs detailed room-wise 3D building layouts from passive monocular image sequences
• Combined SLAM-based camera tracking and vision foundation models with geometric and temporal reasoning

Research Intern

Institute of Automation, Chinese Academy of Sciences (CASIA)

Vision-Language Navigation (VLN) in Intelligent Logistics.

• Integrated USV simulation into CARLA, enabling automated data collection and joint vehicle simulation
• Proposed LogisticsVLN, the first aerial VLN system for window-level terminal delivery scenarios

Bachelor of Engineering

University of Chinese Academy of Sciences (UCAS)

Artificial Intelligence

Visiting Student

University of Oxford

Computer Science (Major), Mathematics (Minor)

SeqLayout3D: Room-wise 3D Building Layout Reconstruction from Monocular Image Sequences

Under Review

Xinyuan Zhang, Yifu Tao, Jan Quenzel, and Maurice Fallon

LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)

Xinyuan Zhang, Yonglin Tian, Fei Lin, Yue Liu, Jing Ma, Kornélia Sára Szatmáry, and Fei-Yue Wang

LogisticsVISTA: 3D Terminal Delivery Services With UAVs, UGVs and USVs Based on Foundation Models and Scenarios Engineering

2024 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)

Yonglin Tian, Fei Lin, Xinyuan Zhang, Jingwei Ge, Yutong Wang, Xingyuan Dai, Yisheng Lv, and Fei-Yue Wang

National Scholarship

Ministry of Education, China

First-Class Undergraduate Academic Scholarship (Top 5% in UCAS)

University of Chinese Academy of Sciences (UCAS)