Research Scientist
Meta, FAIR, New York
liuzhuangthu [at] gmail [dot] com
380 W 33rd St, New York, NY 10001
Google Scholar
Twitter
LinkedIn
GitHub
Zhuang Liu
I'm a Research Scientist at Meta Fundamental AI Research (FAIR), New York. I received my PhD in Computer Science from UC Berkeley EECS, advised by Prof. Trevor Darrell. I was also fortunate to have worked as a visiting researcher / intern at Cornell, Intel Labs, Adobe Research and FAIR. I did my undergrad study in Computer Science at Yao Class, Tsinghua University.
My primary research areas are deep learning and computer vision. I work on deep learning model architectures, training, efficiency, and understanding. Recently, I've also been interested in studying (Vision-)Language Models, and datasets in learning.
I seek to understand the workings of deep learning, and ultimately intelligence in general. I like to explore simple approaches to gain empirical insights into neural networks, their trainings, and behaviors. My research often challenges existing beliefs, e.g., in architectures, training, pruning, and datasets.
I led the development of DenseNet (which won a CVPR Best Paper Award) and ConvNeXt. Both are among the most widely used neural architectures in deep learning and computer vision.
I will be joining Princeton University Department of Computer Science as an Assistant Professor in September 2025!
Prospective students: please apply to Princeton's CS PhD program and mention my name in your application.
Prospective postdoc researchers and current Princeton students: please email me if interested in potential collaboration.
News
[12/2023] Preprints and code on model initialization, model behaviors, and SVRG optimizer released. Congrats to David, Kirill, Oscar, and Yanjie!
[11/2023] Happy to speak and join the panel at the CMU PhD Career Workshop at Pittsburgh
Recent and selected publications (* equal contribution)
Deconstructing Denoising Diffusion Models for Self-Supervised Learning
Xinlei Chen, Zhuang Liu, Saining Xie, Kaiming He
arXiv 2024
Rethinking the Value of Network Pruning
Zhuang Liu*, Mingjie Sun*, Tinghui Zhou, Gao Huang, Trevor Darrell
ICLR 2019
NeurIPS'18 Compact Neural Networks Workshop Best Paper Award
Learning Efficient Convolutional Networks through Network Slimming
Zhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang
ICCV 2017
Previous Publications (* equal contribution)
Anytime Dense Prediction with Confidence Adaptivity
Zhuang Liu, Hung-Ju Wang, Zhiqiu Xu, Trevor Darrell, Evan Shelhamer
ICLR 2022
Regularization Matters in Policy Optimization - An Empirical Study on Continuous Control
Zhuang Liu*, Xuanlin Li*, Bingyi Kang, Trevor Darrell
ICLR 2021
[Paper] [Code] [OpenReview] [Video]
Spotlight Presentation