Tsinghua University
UC Berkeley
Jia DengProfessor · Princeton UniversityResearcher↗
Researcher · Academic
Zhuang Liu
Princeton UniversityAssistant Professor
Liu co-created DenseNet, which helped image-recognition systems reuse information efficiently, and ConvNeXt, which showed that updated traditional vision networks could compete with newer designs.[1] His research showed that some smaller networks train as well from scratch as by shrinking a larger model.[2]
Career & education
Current rolePrinceton University2025-presentAssistant Professor
Princeton University2025-presentPreviously
Meta2021-2025Research Scientist
Meta2021-2025Education
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations117,351As of Nov 1, '26
citations+3,156Since last snapshot, Oct 1, '26
References
- A ConvNet for the 2020sarxiv.org
ConvNeXt coauthorship and competitive performance against transformers.
- Rethinking the Value of Network Pruningarxiv.org
Scope-limited result on training smaller networks from scratch.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 24, 2026 · Checked for accuracy and new information.
