About Me

I am a senior research scientist at Waymo, developing foundation models for prediction and planning in autonomous vehicles. Before joining Waymo, I was a postdoctoral fellow in the Computer Science Department (CSD) at Carnegie Mellon University, co-advised by Prof. Peter Steenkiste and Prof. Srinivasan Seshan. I received my Ph.D. from the AIoT Lab at The Chinese University of Hong Kong, advised by Prof. Guoliang Xing, and my B.Eng. with honors in Electrical Engineering from Zhejiang University.

My research sits at the intersection of embodied AI, robotics, and intelligent transportation. focusing on enabling autonomous systems to perceive, reason, anticipate, and act safely in complex real-world environments. My work has been recognized with multiple best paper and demo awards at ACM MobiCom, the ACM SIGBED Paul Caspi Memorial Dissertation Award (2 recipients worldwide), selection as an MIT EECS Rising Star, and other honors from both academia and industry.

Selected Publications

* Equal contribution (authors listed interchangeably)     † Student mentored by me     ‡ Co-primary authors

ECCO: Leveraging Cross-Camera Correlations for Efficient Live Video Continuous Learning

Yuze He, Ferdi Kossmann, Srinivasan Seshan, Peter Steenkiste
Under review Pre-print
A scalable continuous learning framework that groups cameras with similar data drift to share retraining and efficiently coordinate GPU and bandwidth resources.

EventEye: Towards High-Frequency Perception Enhancement for Autonomous Vehicles Using Infrastructure-Mounted Event Cameras

Jingfei Xia†, Yuze He, Chen Bian, Zhenyu Yan, Guoliang Xing
SenSys 2026
Fusing microsecond-resolution event camera data from roadside infrastructure with vehicle LiDAR to enable detection of fast-moving objects beyond LiDAR’s update limits.

αLiDAR: An Adaptive High-Resolution Panoramic LiDAR System

Yuze He*, Jiahe Cui*†, Jianwei Niu, Zhenchao Ouyang, Guoliang Xing
🏆MobiCom 2024 Best Artifact Award (2 of 494 submissions)
🏆MobiCom 2024 Best Demo Award Runner-up
MobiCom 2024 Demo Video (6.5k+ YouTube views) Code (200+ Github 🌟)
An adaptive LiDAR system that actively directs scanning to expand field of view, remove blind spots, and focus on task-relevant regions.

VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving

Yuze He, Chen Bian, Jingfei Xia, Shuyao Shi, Zhenyu Yan, Qun Song, Guoliang Xing
🏆MobiCom 2023 Best Community Contribution Award (2 of 377 submissions)
🏅Gold Prize at the 49th International Exhibition of Inventions Geneva
🏆Best Paper Award at the 2023 International Doctoral Forum
MobiCom 2023 Demo Video Code Dataset
The first system that leverages roadside infrastructure’s static, persistent view to enhance online HD map construction for autonomous driving.

AutoMatch: Leveraging Traffic Camera to Improve Perception and Localization of Autonomous Vehicles

Yuze He, Li Ma, Jiahe Cui, Zhenyu Yan, Guoliang Xing, Sen Wang, Qintao Hu, Chen Pan
SenSys 2022
Leveraging ubiquitous traffic cameras to enhance perception and localization in autonomous driving.

VI-Eye: Semantic-based 3D Point Cloud Registration for Infrastructure-assisted Autonomous Driving

Yuze He, Li Ma, Zhehao Jiang, Yi Tang, Guoliang Xing
MobiCom 2021 Teaser Video
The first system that fuses roadside infrastructure point clouds with a vehicle’s point cloud to help it see farther and see through occlusions.

Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving

Shuyao Shi‡, Neiwen Ling‡, Zhehao Jiang‡, Xuan Huang‡, Yuze He, Xiaoguang Zhao, Bufang Yang, Chen Bian, Jingfei Xia, Zhenyu Yan, Raymond W. Yeung, and Guoliang Xing
🏆MobiCom 2024 Best Artifact Award Runner-up
MobiCom 2024
The end-to-end software and hardware design, and real-world deployment, of a campus-scale smart roadside infrastructure system for assisting autonomous driving.

VILAM: Infrastructure-assisted 3D Visual Localization and Mapping for Autonomous Driving

Jiahe Cui, Shuyao Shi, Yuze He, JianWei Niu, Guoliang Xing, Zhenchao Ouyang
NSDI 2024
Leveraging distributed LiDAR on roadside infrastructure as global references to correct visual SLAM drift, enabling accurate vehicular SLAM without GNSS or loop closures.

Other Projects

Smart Car Race

Kai Wang*, Li Ma*, Yuze He*
National Undergraduate Smart Car Race of China, 2018

Selected Honors & Awards

Service