- Embodied Navigation Foundation Model (NavFoM), Arxiv Preprint.
- TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking, Arxiv Preprint.
- TrackVLA: Embodied Visual Tracking in the Wild, CoRL 2025.
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks, RSS 2025.
- EF-Calib: Spatiotemporal Calibration of Event- and Frame-based Cameras Using Continuous-Time Trajectories, IEEE Robotics and Automation Letters, 2024.
- Spatially Compact Visual Navigation System for Automated Suturing Robot Toward Oral and Maxillofacial Surgery, IEEE Transactions on Instrumentation and Measurement, 2024.
- CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants, IEEE Transactions on Visualization and Computer Graphics, 2024.
Research Experience
Current: Research Intern at ByteDance Seed Robotics; Former: Research Intern at GALBOT (an embodied AI startup), Supervisors: Prof. He Wang and Dr. Zhizheng Zhang.
Education
PhD: School of Advanced Manufacturing and Robotics, Peking University, Advisor: Prof. Junzhi Yu; Bachelor's: Robotics, Beijing Institute of Technology, 2021, Advisor: Prof. Huaping Wang.
Background
Research Interests: Embodied AI, with a specific focus on visual-language navigation and multimodal robot perception and planning. Brief Introduction: Currently a fifth-year PhD student at the School of Advanced Manufacturing and Robotics, Peking University.