Zhijian Liu

Zhijian Liu
zhijian [at] mit (dot) edu

I am a fifth-year PhD student at MIT, advised by Song Han. My research focuses on efficient deep learning and its applications in computer vision and robotics.

Before coming to MIT, I received my B.Eng. in Computer Science from Shanghai Jiao Tong University. During my undergrad, I was fortunate to work with Jiajun Wu, Josh Tenenbaum and Bill Freeman.

Email / Google Scholar / LinkedIn / GitHub

News

I will commit 2 hours every week to provide guidance, suggestions, and/or mentorships for students from underrepresented groups or whoever is in need. Please fill in this form if you are interested.
[2021-06] I was awarded Qualcomm Innovation Fellowship. Thanks, Qualcomm!
[2021-06] Our SPVCNN++ won the first place in nuScenes LiDAR Segmentation Challenge.
[2021-03] Our HAQ has been integrated into Intel's OpenVINO toolkit.

Publications

SemAlign: Annotation-Free Camera-LiDAR Calibration with Semantic Alignment Loss
Zhijian Liu*, Haotian Tang*, Sibo Zhu*, Song Han
IROS 2021 / Project Page

LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision
Zhijian Liu, Simon Stent, Jie Li, John Gideon, Song Han
ICCV 2021 / arXiv / Project Page

Efficient and Robust LiDAR-Based End-to-End Navigation
Zhijian Liu*, Alexander Amini*, Sibo Zhu, Sertac Karaman, Song Han, Daniela L. Rus
ICRA 2021 / arXiv / Project Page

Differentiable Augmentation for Data-Efficient GAN Training
Shengyu Zhao, Zhijian Liu, Ji Lin, Jun-Yan Zhu, Song Han
NeurIPS 2020

Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Haotian Tang*, Zhijian Liu*, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, Song Han
ECCV 2020 / Paper / arXiv / Project Page

DataMix: Efficient Privacy-Preserving Edge-Cloud Inference
Zhijian Liu*, Zhanghao Wu*, Chuang Gan, Ligeng Zhu, Song Han
ECCV 2020

GAN Compression: Efficient Architectures for Interactive Conditional GANs
Muyang Li, Ji Lin, Yaoyao Ding, Zhijian Liu, Jun-Yan Zhu, Song Han
CVPR 2020 / arXiv / Code

APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
Tianzhe Wang*, Kuan Wang*, Han Cai, Ji Lin, Zhijian Liu, Hanrui Wang, Yujun Lin, Song Han
CVPR 2020

Lite Transformer with Long-Short Range Attention
Zhanghao Wu*, Zhijian Liu*, Ji Lin, Yujun Lin, Song Han
ICLR 2020

AutoML for Architecting Efficient and Specialized Neural Networks
Han Cai*, Ji Lin*, Yujun Lin*, Zhijian Liu*, Kuan Wang*, Tianzhe Wang*, Ligeng Zhu*, Song Han
IEEE Micro 2020

Point-Voxel CNN for Efficient 3D Deep Learning
Zhijian Liu*, Haotian Tang*, Yujun Lin, Song Han
NeurIPS 2019 / Paper / arXiv / Project Page / Code / NVIDIA News
Spotlight Presentation

Deep Leakage from Gradients
Ligeng Zhu, Zhijian Liu, Song Han
NeurIPS 2019 / Paper / arXiv / Project Page / Code

HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Kuan Wang*, Zhijian Liu*, Yujun Lin*, Ji Lin, Song Han
CVPR 2019 / Paper / arXiv / Project Page / Code
Oral Presentation

Unsupervised Discovery of Parts, Structure, and Dynamics
Zhenjia Xu*, Zhijian Liu*, Chen Sun, Kevin Murphy, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
ICLR 2019 / Paper / arXiv / Project Page

Learning to Exploit Stability for 3D Scene Parsing
Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
NeurIPS 2018 / Paper / Project Page

Physical Primitive Decomposition
Zhijian Liu, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
ECCV 2018 / Paper / arXiv / Project Page

AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Yihui He*, Ji Lin*, Zhijian Liu, Hanrui Wang, Li-Jia Li, Song Han
ECCV 2018 / Paper / arXiv / Project Page / Code

Design and source code from Jon Barron's website