
Research Scientist at FAIR
Email: liuzhuangthu at gmail.com
Google Scholar /
GitHub /
LinkedIn /
Twitter
Zhuang Liu
I'm a Research Scientist at FAIR, Meta AI. I received my PhD from UC Berkeley (Dissertation), advised by Prof. Trevor Darrell. I was fortunate to have worked as a visiting researcher or an intern at Cornell University, Intel Labs, Adobe Research and FAIR. I received my Bachelor's degree from Yao Class at Tsinghua University.
My research aims to advance representation learning by developing novel model architectures and learning algorithms, with a focus on efficiency and scalability in specific areas to promote practical progress. I also place an emphasis on exploring simple and baseline methods to gain insights into the workings of deep learning. My work on DenseNet received CVPR Best Paper Award in 2017.
Selected Publications
(* equal contribution)![]() |
Dropout Reduces UnderfittingZhuang Liu*, Zhiqiu Xu*, Joseph Jin, Zhiqiang Shen, Trevor Darrell ICML 2023 |
![]() |
A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie CVPR 2022 |
![]() |
Anytime Dense Prediction with Confidence AdaptivityZhuang Liu, Hung-Ju Wang, Zhiqiu Xu, Trevor Darrell, Evan Shelhamer ICLR 2022 |
![]() |
Regularization Matters in Policy Optimization - An Empirical Study on Continuous ControlZhuang Liu*, Xuanlin Li*, Bingyi Kang, Trevor Darrell ICLR 2021 [Paper] [OpenReview] [Video] [Code] Spotlight Presentation |
![]() |
Rethinking the Value of Network PruningZhuang 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 SlimmingZhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang ICCV 2017 |
![]() |
Densely Connected Convolutional NetworksGao Huang*, Zhuang Liu*, Laurens van der Maaten, Kilian Weinberger CVPR 2017 [Paper] [Video] [TPAMI version] [Code] CVPR Best Paper Award |
Full List of Publications
![]() |
Dropout Reduces UnderfittingZhuang Liu*, Zhiqiu Xu*, Joseph Jin, Zhiqiang Shen, Trevor Darrell arXiv 2023 |
![]() |
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked AutoencodersSanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie CVPR 2023 |
![]() |
Exploring Simple and Transferable Recognition-Aware Image ProcessingZhuang Liu, Hungju Wang, Tinghui Zhou, Zhiqiang Shen, Bingyi Kang, Evan Shelhamer, Trevor Darrell TPAMI 2022 |
![]() |
A ConvNet for the 2020sZhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie CVPR 2022 |
![]() |
Anytime Dense Prediction with Confidence AdaptivityZhuang Liu, Hung-Ju Wang, Zhiqiu Xu, Trevor Darrell, Evan Shelhamer ICLR 2022 |
![]() |
Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization SpaceArnav Chavan, Zhiqiang Shen, Zhuang Liu, Zechun Liu, Kwang-Ting Cheng, Eric Xing CVPR 2022 |
![]() |
Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation LearningZhiqiang Shen, Zechun Liu, Zhuang Liu, Marios Savvides, Trevor Darrell AAAI 2022 |
![]() |
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot LearningYinbo Chen, Zhuang Liu, Huijuan Xu, Trevor Darrell, Xiaolong Wang ICCV 2021 |
![]() |
SensAI: Fast ConvNets Serving on Live Data via Class ParallelismGuanhua Wang, Zhuang Liu, Siyuan Zhuang, Brandon Hsieh, Joseph E. Gonzalez, Trevor Darrell, Ion Stoica Machine Learning and Systems 2021 |
![]() |
Regularization Matters in Policy Optimization - An Empirical Study on Continuous ControlZhuang Liu*, Xuanlin Li*, Bingyi Kang, Trevor Darrell ICLR 2021 [Paper] [Code] [OpenReview] [Video] Spotlight Presentation |
![]() |
Test-Time Training for Out-of-Distribution GeneralizationYu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt ICML 2020 |
![]() |
MSeg: A Composite Dataset for Multi-domain Semantic SegmentationJohn Lambert*, Zhuang Liu*, Ozan Sener, James Hays, Vladlen Koltun CVPR 2020 |
![]() |
Few Sample Knowledge Distillation for Efficient Network CompressionTianhong Li, Jianguo Li, Zhuang Liu, Changshui Zhang CVPR 2020 |
![]() |
Few-shot Object Detection via Feature ReweightingBingyi Kang*, Zhuang Liu*, Xin Wang, Fisher Yu, Jiashi Feng, Trevor Darrell ICCV 2019 |
![]() |
Rethinking the Value of Network PruningZhuang Liu*, Mingjie Sun*, Tinghui Zhou, Gao Huang, Trevor Darrell ICLR 2019 NeurIPS'18 Compact Neural Networks Workshop Best Paper Award |
![]() |
DSOD: Learning Deeply Supervised Object Detectors from ScratchZhiqiang Shen*, Zhuang Liu*, Jianguo Li, Yu-Gang Jiang, Yurong Chen, Xiangyang Xue ICCV 2017 |
![]() |
Learning Efficient Convolutional Networks through Network SlimmingZhuang Liu, Jianguo Li, Zhiqiang Shen, Gao Huang, Shoumeng Yan, Changshui Zhang ICCV 2017 |
![]() |
Densely Connected Convolutional NetworksGao Huang*, Zhuang Liu*, Laurens van der Maaten, Kilian Weinberger CVPR 2017 [Paper] [Code] [Video] [TPAMI version] CVPR Best Paper Award |
![]() |
Snapshot Ensembles: Train 1, Get M for FreeGao Huang, Yixuan Li, Geoff Pleiss, Zhuang Liu, John Hopcroft, Kilian Weinberger ICLR 2017 |
![]() |
Deep Networks with Stochastic DepthGao Huang, Yu Sun, Zhuang Liu, Daniel Sedra, Kilian Weinberger ECCV 2016 Spotlight Presentation |