Zhuang Liu's Homepage

Assistant Professor

Department of Computer Science

Princeton University

Email: zhuangl@princeton.edu

35 Olden St, Princeton, NJ 08540

Google Scholar Twitter
LinkedIn GitHub

Zhuang Liu
[Pronouncing Zhuang]

I'm an Assistant Professor of Computer Science at Princeton University. I received my Ph.D. in Computer Science from UC Berkeley, advised by Trevor Darrell, and B.S. in Computer Science from Yao Class, Tsinghua University. Before joining Princeton, I was a research scientist at Meta FAIR, New York. I also worked as a research intern at Cornell, Intel, Adobe, and FAIR.

My research areas are deep learning and computer vision, with an emphasis on understanding how models work and behave. My work spans vision and language, unified by a focus on deep learning methods, representations, and architectures.

I explore simple approaches to gain empirical insights into neural networks. My research often challenges existing beliefs, e.g., in arch itectures, training, pruning, and data sets.

Research intern / visiting positions: please fill out this form to get in touch.

Research Group

PhD Students

• Wenhao Chai

• Tony Chen

• Sachin Konan

• Taiming Lu

• Zhuorui Ye

• David Yin

• Boya Zeng

PLI Postdoctoral Fellows

• Xingyu Fu

• Gabe Sarch

Assistant Professor

Department of Computer Science

Princeton University

Email: zhuangl@princeton.edu

35 Olden St, Princeton, NJ 08540

Google Scholar Twitter
LinkedIn GitHub

Zhuang Liu
[Pronouncing Zhuang]

Research Group

News

Recent and selected publications (* equal contribution, for full list please see Google Scholar)

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Transformers without Normalization

Idiosyncrasies in Large Language Models

A Decade's Battle on Dataset Bias: Are We There Yet?

Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Understanding Bias in Large-Scale Visual Datasets

Massive Activations in Large Language Models

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

A Simple and Effective Pruning Approach for Large Language Models

ImageBind: One Embedding Space To Bind Them All

A ConvNet for the 2020s

Test-Time Training for Out-of-Distribution Generalization

Rethinking the Value of Network Pruning

Learning Efficient Convolutional Networks through Network Slimming

Densely Connected Convolutional Networks

Deep Networks with Stochastic Depth

Others

Assistant Professor

Department of Computer Science

Princeton University

Email: zhuangl@princeton.edu

35 Olden St, Princeton, NJ 08540

Google Scholar Twitter LinkedIn GitHub

Research Group

News

Recent and selected publications (* equal contribution, for full list please see Google Scholar)

MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Transformers without Normalization

Idiosyncrasies in Large Language Models

A Decade's Battle on Dataset Bias: Are We There Yet?

Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Understanding Bias in Large-Scale Visual Datasets

Massive Activations in Large Language Models

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

A Simple and Effective Pruning Approach for Large Language Models

ImageBind: One Embedding Space To Bind Them All

A ConvNet for the 2020s

Test-Time Training for Out-of-Distribution Generalization

Rethinking the Value of Network Pruning

Learning Efficient Convolutional Networks through Network Slimming

Densely Connected Convolutional Networks

Deep Networks with Stochastic Depth

Others

Google Scholar Twitter
LinkedIn GitHub