Hey, I am Hang Zhao, an Assistant Professor at IIIS, Tsinghua University, Principle Investigator of MARS Lab. My research interests are multi-modal machine learning, autonomous driving and robot learning. Check out our MARS Lab Website for a full list of research projects and publications.
I was a Research Scientist at Waymo (known as Google's self-driving project) from 2019 to 2020.
Before that, I got my Ph.D. degree at MIT in 2019 under the supervision of Professor Antonio Torralba (the Great Torralba!). Before MIT, I received my B.S. from Zhejiang University in 2013.
I am actively looking for PostDoc/PhD/BS students and engineers with CS/EE background to join my team. If you would like to work with me, feel free to drop me an email with your resume.
Contact Info
Address: Tsinghua University Science Park, C19
E-mail: ZhaoHang0124 (at) gmail.com
Selected Projects
Humanoid Parkour LearningHot
Ziwen Zhuang, Shenzhe Yao, Hang Zhao
CoRL 2024 "The first humanoid robot that learns to parkour!" PaperProject
DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language ModelsHot
Xiaoyu Tian, Junru Gu, Bailin Li, Yicheng Liu, Yang Wang, Zhiyong Zhao, Kun Zhan Peng Jia, Xianpeng Lang, Hang Zhao
CoRL 2024 "Slow-Fast Dual System for autnomous driving!" PaperProject
Latent Consistency Models: Synthesizing High-Resolution Images With Few-Step InferenceHot
Simian Luo, Yiqin Tan, Longbo Huang, Jian Li, Hang Zhao "Generating high-resolution images in only 2-4 steps!" LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
Simian Luo, Yiqin Tan, Suraj Patil, Daniel Gu, Patrick von Platen, Apolinário Passos, Longbo Huang, Jian Li, Hang Zhao "Accelerating your LoRA model by 5x without training!" LCM PaperLCM-LoRA ReportDemoProject
Robot Parkour LearningHot
Ziwen Zhuang, Zipeng Fu, Jianren Wang, Christopher G Atkeson, Sören Schwertfeger, Chelsea Finn, Hang Zhao CoRL 2023 Oral Best System Paper Finalist (Top 3) "Robot parkour skills empowered by onboard vision and a neural network!"
VCAD: Vision-Centric Autonomous DrivingHot
Hang Zhao, Yue Wang, Yilun Wang, Justin Solomon, Vitor Guizilini, et al. "A research effort pushing the frontiers of camera-centric autonomous driving technology."
Neural Map Prior for Autonomous Driving
Xuan Xiong, Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, Hang Zhao CVPR 2023 "A neural representation of HD maps to improve local map inference."
HDMapNet: An Online HD Map Construction and Evaluation Framework
Qi Li, Yue Wang, Yilun Wang, Hang Zhao CVPR 2021 Workshop best paper, ICRA 2022 "HD map learning from onboard sensors!"
Neural Dubber: Dubbing for Videos According to Scripts
Chenxu Hu, Qiao Tian, Tingle Li, Yuping Wang, Yuxuan Wang, Hang Zhao NeurIPS 2021 "Automatic video dubbing driven by a neural network!"
DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D QueriesHot
Yue Wang, Vitor Campagnolo Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, Justin Solomon CoRL 2021 "A new paradigm of 3D object detection from 2D images!"
On Feature Decorrelation in Self-Supervised LearningHot
Tianyu Hua, Wenxiao Wang, Zihui Xue, Yue Wang, Sucheng Ren, Hang Zhao ICCV 2021 Oral "It reveals the connection between model collapse and feature correlations!"
DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
Junru Gu, Chen Sun, Hang Zhao ICCV 2021 "A SOTA anchor-free and end-to-end multi-trajectory prediction model"
VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized RepresentationHot
Jiyang Gao, Chen Sun, Hang Zhao, Yi Shen,
Dragomir Anguelov, Congcong Li, Cordelia Schmid
In Proc. Computer Vision and Pattern Recognition (CVPR) 2020
Scalability in Perception for Autonomous Driving: Waymo Open Dataset
Pei Sun et al.
In Proc. Computer Vision and Pattern Recognition (CVPR) 2020
Seattle (virtual), June. 2020
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
Hang Zhao, Zhicheng Yan, Lorenzo Torresani, Antonio Torralba
In Proc. International Conference on Computer Vision (ICCV)
Seoul, Korea, Oct. 2019 "A large-scale dataset for temporal action localization and recognition."
The Sound of PixelsHot
Hang Zhao, Chuang Gan, Andrew Rouditchenko, Carl Vondrick, Josh McDermott, Antonio Torralba
In Proc. European Conference on Computer Vision (ECCV)
Munich, Germany, Sep. 2018 "Listen to the sound of pixels!" Paper (arXiv)Project PageCodeNews Coverage
Through-Wall Human Pose Estimation Using Radio SignalsHot
Mingmin Zhao, Tianhong Li, Mohammad Alsheikh, Yonglong Tian, Hang Zhao, Antonio Torralba, Dina Katabi
In Proc. Computer Vision and Pattern Recognition (CVPR)
Salt Lake City, Utah, June. 2018 PaperProject PageNews Coverage
Scene Parsing through ADE20K DatasetHot
Bolei Zhou, Hang Zhao, Xavier Puig, Sanja Fidler, Adela Barriuso, Antonio Torralba
In Proc. Computer Vision and Pattern Recognition (CVPR)
Honolulu, Hawaii, July. 2017 PaperDatasetCodeOnline Demo
Semantic Understanding of Scenes through the ADE20K Dataset
Bolei Zhou, Hang Zhao, Xavier Puig, Tete Xiao, Sanja Fidler, Adela Barriuso, Antonio Torralba
International Journal on Computer Vision 2018 (IJCV)
Loss Functions for Neural Networks for Image Processing Hot Hang Zhao, Orazio Gallo, Iuri Frosio and Jan Kautz
arXiv:1511.08861
IEEE Transactions on Computational Imaging 2017 (TCI)
Duckietown: an Open, Inexpensive and Flexible Platform for Autonomy Education and Research
IEEE International Conference on Robotics and Automation (ICRA)
Singapore, May. 2017 "We are building an open-source education and research platform for autonomous driving. " PaperVideoProject PageCodeNews Coverage
Unbounded High Dynamic Range Photography using a Modulo Camera Hot Hang Zhao, Boxin Shi, Christy Fernandez-Cull, Sai-Kit Yeung and Ramesh Raskar
In Proc. International Conference on Computational Photography (ICCP)
Houston, USA, Apr. 2015 (Acceptance Rate: 24%)
Oral Presentation [Best Paper runner-up]
