Gongjun Xu

Full Professor, University of Michigan - Ann Arbor

Joined

July 2019

Names

Gongjun Xu

Emails

****@umich.edu (Confirmed)

Personal Links

Homepage

Career & Education History

Full Professor

University of Michigan - Ann Arbor (umich.edu)

Present

PhD student

Columbia University (columbia.edu)

2008 – 2013

Advisors, Relations & Conflicts

PhD Advisee

Jing Ouyang

2019 – 2024

PhD Advisee

Yinqiu He

2017 – 2021

PhD Advisee

Yuqi Gu

2017 – 2020

PhD Advisor

Zhiliang Ying

2009 – 2013

PhD Advisor

Jingchen Liu

2009 – 2013

Expertise

No areas of expertise listed

Publications

Efficient Synthetic Network Generation via Latent Embedding Reconstruction
Feifan Jiang, Yinan Bu, Shihao Wu, Gongjun Xu, Ji Zhu
- Submitted to ICLR 2026
- Readers: Everyone
ReLaSH: Reconstructing Joint Latent Spaces for Efficient Generation of Synthetic Hypergraphs with Hyperlink Attributes
Feiyan Ma, Shihao Wu, Gongjun Xu, Ji Zhu
- ICLR 2026 Poster
- Readers: Everyone
Bridging Human and LLM Judgments: Understanding and Narrowing the Gap
Felipe Maia Polo, Xinhe Wang, Mikhail Yurochkin, Gongjun Xu, Moulinath Banerjee, Yuekai Sun
- NeurIPS 2025 poster
- Readers: Everyone
tinyBenchmarks: evaluating LLMs with fewer examples
Felipe Maia Polo, Lucas Weber, Leshem Choshen, Yuekai Sun, Gongjun Xu, Mikhail Yurochkin
- ICML 2024 Poster
- Readers: Everyone
Physically informed machine-learning algorithms for the identification of two-dimensional atomic crystals
Laura Zichi, Tianci Liu, Elizabeth Drueke, Liuyan Zhao, Gongjun Xu
- 13 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Estimating three-and four-parameter MIRT models with importance-weighted sampling enhanced variational auto-encoder
Tianci Liu, Chun Wang, Gongjun Xu
- 13 May 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Survival Analysis via Ordinary Differential Equations
Weijing Tang, Kevin He, Gongjun Xu, Ji Zhu
- 30 Mar 2022
- OpenReview Archive Direct Upload
- Readers: Everyone

Gongjun Xu

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Efficient Synthetic Network Generation via Latent Embedding Reconstruction

ReLaSH: Reconstructing Joint Latent Spaces for Efficient Generation of Synthetic Hypergraphs with Hyperlink Attributes

Bridging Human and LLM Judgments: Understanding and Narrowing the Gap

tinyBenchmarks: evaluating LLMs with fewer examples

Physically informed machine-learning algorithms for the identification of two-dimensional atomic crystals

Estimating three-and four-parameter MIRT models with importance-weighted sampling enhanced variational auto-encoder

Survival Analysis via Ordinary Differential Equations

Co-Authors