Jing Zhu

About Me

I am Jing Zhu, a fourth year PhD student at the University of Michigan, with Danai Koutra.

Before that, I obtained my B.S.E. from both the University of Michigan and Shanghai Jiao Tong University, and I worked with Andrew Owens.

I am interested in building multilingual, multimodal and multidomain LLMs.

Research Interns

[Google DeepMind]: 2025/05 - Present

[AWS AI]: 2022/05 - 2022/11

News

[2024/09] "Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning is accepted at CVPR'25!
[2024/09] "On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks is accepted at NeurIPS'24!
[2024/09] "Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation is accepted at EMNLP'24!
[2024/04] "TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning is accepted at SIGIR'24!
[2023/10] "Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices is accepted at WSDM'24!
[2022/09] "Touch and Go: Learning from Human-Collected Vision and Touch is accepted at NeurIPS'22!
[2022/08] "CAPER: Coarsen, Align, Project, Refine - A General Multilevel Framework for Network Alignment is accepted at CIKM'22!
[2021/08] "NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases is accepted at EMNLP'21!
[2020/12] "Node Proximity Is All You Need: A Unified Framework for Proximity-Preserving and Structural Node and Graph Embedding." is accepted at SDM'21!

Book Chapter

Fact Summarization for Personalized Knowledge Graphs

Danai Koutra, Davide Mottin, Jing Zhu

Personal Knowledge Graphs (PKGS): Methodology, Tools and Applications

Publications

[11] DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data. [link] [code]

Yuhang Zhou*, Jing Zhu*, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang

Arxiv 2025

[10] Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning. [link] [code]

Jing Zhu, Yuhang Zhou, Shengyi Qian, Zhongmou He, Tong Zhao, Neil Shah, Danai Koutra

CVPR 2025

[9] On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks. [link] [code]

Jiong Zhu*, Gaotang Li, Yao-An Yang, Jing Zhu, Xuehao Cui, Danai Koutra

Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

[8] Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation. [link] [code]

Yuhang Zhou*, Jing Zhu*, Paiheng Xu, Xiaoyu Liu, Xiyao Wang, Danai Koutra, Wei Ai, Furong Huang

The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024 Findings)

[7] LinkGPT: Teaching Large Language Models To Predict Missing Links. [link] [code]

Zhongmou He, Jing Zhu, Shengyi Qian, Joyce Y. Chai, Danai Koutra

Arxiv 2024

[6] TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning. [link] [code]

Jing Zhu, Xiang Song, Vassilis N. Ioannidis, Danai Koutra, Christos Faloutsos

ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024)

[5] Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practices.[link] [code]

Jing Zhu*, Yuhang Zhou*, Vassilis N. Ioannidis, Shengyi Qian, Wei Ai, Xiang Song, Danai Koutra

The 17th ACM International Conference on Web Search and Data Mining (WSDM 24)

Best paper award at MLoG [Slides]

[4] Touch and Go: Learning from Human-Collected Vision and Touch. [link] [code]

Fengyu Yang, Chenyang Ma, Jiacheng Zhang, Jing Zhu, Wenzhen Yuan, Andrew Owens

Neural Information Processing Systems (NeurIPS 22 Dataset and Benchmark)

[3] CAPER: Coarsen, Align, Project, Refine - A General Multilevel Framework for Network Alignment. [link] [code]

Jing Zhu, Danai Koutra, Mark Heimann

International Conference on Information and Knowledge Management (CIKM 22)

[2] NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases. [link] [code]

Tara Safavi, Jing Zhu, Danai Koutra

The 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 21)

[1] Node Proximity Is All You Need: A Unified Framework for Proximity-Preserving and Structural Node and Graph Embedding. [link] [code]

Jing Zhu*, Xingyu Lu*, Mark Heimann, Danai Koutra

SIAM International Conference on Data Mining (SDM 21)

Selected Awards

DEI Award, CVPR 2024
Best paper Award, MLoG 2024
Two Sigma Fellowship Finalist
CIKM Travel Award, SIGIR. Oct. 2022
KDD Travel Award, SIGKDD. Aug. 2022
CSE fellowship, University of Michigan. 2021-2022
Rackham Travel Grant, University of Michigan. Nov. 2021.
SDM Travel Award, SIAM. Apr. 2021.
James B. Angell Scholar, University of Michigan. Mar. 2021.
Jackson and Muriel Lum Scholarship, University of Michigan. 2019-2021
Excellent Undergraduate Scholarship, Shanghai Jiao Tong University. Nov. 2018, Nov. 2019.

Teaching

EECS476 Data Mining, University of Michigan. 2021 Winter.
EECS496 Major Design Experience-Professionalism, University of Michigan. 2020 Fall.
VV285 Honors Mathematics III, Shanghai Jiao Tong University. 2019 Summer.
VV186 Honors Mathematics II, Shanghai Jiao Tong University. 2018 Fall.

Academic Service

Review: TKDD, NeurIPS, AAAI, KDD, ECML-PKDD, SDM, LoG, NeurIPS New Frontiers in Graph Learning
Organizer: LoG Meetup 2023

Misc

I would love to help minority students in CS research. Feel free to reach out if you need anything.
My research journey starts during high school with my great advisor SHI Guochao. We investigate the effect of Cactus Optunia on Bronchitis and won multiple innovation awards including Honorable Mention in Shing-Tung Yau High School Science Award.