Jindong Wang

Assistant Professor, William & Mary
jwang80 [at] wm.edu, jindongwang [at] outlook.com
Integrated Science Center 2273, Williamsburg, VA
Google scholar | DBLP | Github | Twitter/X | LinkedIn | Zhihu | Bilibili || CV CV (Chinese)

PhD and intern application: 2025 fall PhD is fulfilled. You can either apply for future PhDs or apply for Internship or collaboration. [PhD and interns] [Chinese version]

Research interest: (See this page for more details)

General ML and AI: To make AI systems more robust, trustworthy, and responsible. Key areas: robust machine learning, OOD / domain generalization, transfer learning, semi-supervised learning, federated learning, and related applications. These days, I’m particularly interested in ML with foundation models.
Philosophy of language models: We mainly focus on understanding the potential and limitation of large foundation models. Related topics: LLM evaluation and enhancement, and agent behavior.
AI for social sciences: How to measure the impact of generative AI on different domains? How to assist interdisciplinary domains using powerful AI models? How to use existing social science knowledge to help us better understand AI behaviors?

I am open to industry and university visit, consultant, and more collaboration!

Dr. Jindong Wang is a Tenure-Track Assistant Professor at Data Science, William & Mary. He is also a faculty member at AI safety community, Future of Life Institute. He was a Senior Researcher in Microsoft Research Asia from 2019 to 2024. His research interest includes machine learning, large language and foundation models, and AI for social science. Since 2022, he has been selected by Stanford University as one of the World’s Top 2% Highly Cited Scientists and one of the Most Influential AI Scholars by AMiner. He serves as the associate editor of IEEE Transactions on Neural Networks and Learning Systems (TNNLS), guest editor for ACM Transactions on Intelligent Systems and Technology (TIST), area chair for ICML, NeurIPS, ICLR, KDD, ACL, ACMMM, and ACML, SPC of IJCAI and AAAI. He has published over 60 papers with 17000+ citations (H-index 47) at leading conferences and journals such as ICML, ICLR, NeurIPS, TPAMI, IJCV etc. His research is reported by Forbes, MIT Technology Review, and other international media. He received best papers awards at several internation conferences and workshops. He published a book Introduction to Transfer Learning and gave tutorials at IJCAI’22, WSDM’23, KDD’23, AAAI’24, AAAI’25, and CVPR’25. He leads several impactful open-source projects, including transferlearning, PromptBench, torchSSL, and USB, which received over 20K stars. He obtained his Ph.D from University of Chinese Academy of Sciences in 2019 with the excellent PhD dissertation and a bachelor’s degree from North China University of Technology in 2014.

News

May 24, 2025	Three papers accepted by ACL 2025, including one main, one findings, and one demo paper. Congrats!
May 01, 2025	Four papers are accepted by ICML 2025. Congrats!
Apr 20, 2025	Invited to be a faculty member at the AI Safety Community of Future of Life Institute!
Apr 18, 2025	Our ICCV 2025 workshop proposal “Trustworthy Study Transfers from Classical to Foundation Models” is accepted! See you in Hawaii!
Mar 20, 2025	We are organizing the International Workshop on Federated Learning with Generative AI In Conjunction with IJCAI 2025 (FedGenAI-IJCAI’25)!
Mar 18, 2025	The journal verison of noisy model learning got accepted by TPAMI! Congrats! [Paper]
Mar 17, 2025	I was awarded the William & Mary Faculty Research Award!
Mar 04, 2025	Our paper “Scito2M: A 2 Million, 30-Year Cross-disciplinary Dataset for Temporal Scientometric Analysis” got the Best Paper Award at AAAI 2025 Good Data workshop! Congrats! [Paper]

Selected publications

Impact of Noisy Supervision in Foundation Model Learning

Hao Chen, Zihan Wang, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, Bhiksha Raj, and Jindong Wang^#

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2025 | [ arXiv Code ]
Slight Corruption in Pre-training Data Makes Better Diffusion Models

Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang^# , and Bhiksha Raj

Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS) 2024 | [ arXiv Code Zhihu ]

(Spotlight)
Competeai: Understanding the competition behaviors in large language model-based agents

Qinlin Zhao, Jindong Wang^# , Yixuan Zhang, Yiqiao Jin, Kaijie Zhu, Hao Chen, and Xing Xie

International Conference on Machine Learning (ICML) 2024 | [ arXiv Code ]

(Oral)
The good, the bad, and why: Unveiling emotions in generative ai

Cheng Li, Jindong Wang^# , Yixuan Zhang, Kaijie Zhu, Xinyi Wang, Wenxin Hou, Jianxun Lian, Fang Luo, Qiang Yang, and Xing Xie

International Conference on Machine Learning (ICML) 2024 | [ arXiv Code ]
DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization

Wang Lu, Jindong Wang^# , Xinwei Sun, Yiqiang Chen, Xiangyang Ji, Qiang Yang, and Xing Xie

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2024 | [ arXiv Code Zhihu ]
DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

Kaijie Zhu, Jiaao Chen, Jindong Wang^# , Neil Zhenqiang Gong, Diyi Yang, and Xing Xie

International Conference on Learning Representation (ICLR) 2024 | [ arXiv Code ]

(Spotlight (Top 5%))
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

Hao Chen, Jindong Wang^# , Ankit Shah, Ran Tao, Hongxin Wei, Xing Xie, Masashi Sugiyama, and Bhiksha Raj

International Conference on Learning Representation (ICLR) 2024 | [ arXiv Code Zhihu ]

(Spotlight (Top 5%))

Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling

Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang^# , Manabu Okumura, and Takahiro Shinozaki

Advances in Neural Information Processing Systems (NeurIPS) 2021 | [ arXiv PDF Code Slides Video Zhihu ]

(900+ citations; Top 17 most cited NeurIPS papers in the past 5 years)

@article{zhang2021flexmatch,
  title = {Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling},
  author = {Zhang, Bowen and Wang, Yidong and Hou, Wenxin and Wu, Hao and Wang, Jindong and Okumura, Manabu and Shinozaki, Takahiro},
  journal = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {34},
  year = {2021},
  bibtex_show = {true},
  corr = {true},
  abbr = {NeurIPS},
  arxiv = {https://arxiv.org/abs/2110.08263},
  pdf = {http://jd92.wang/assets/files/flexmatch_nips21.pdf},
  code = {https://github.com/TorchSSL/TorchSSL},
  zhihu = {https://zhuanlan.zhihu.com/p/422930830},
  video = {https://www.youtube.com/watch?v=aYuUwyZl_WY},
  slides = {https://www.jianguoyun.com/p/DXeFVg8QjKnsBRibj54E},
  selected = {true},
  special = {900+ citations; Top 17 most cited NeurIPS papers in the past 5 years}
}

Adarnn: Adaptive learning and forecasting of time series

Yuntao Du, Jindong Wang^# , Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu, and Chongjun Wang

The 30th ACM International Conference on Information & Knowledge Management (CIKM) 2021 | [ arXiv PDF Code ]

(Paperdigest most influencial CIKM paper)

@inproceedings{du2021adarnn,
  title = {Adarnn: Adaptive learning and forecasting of time series},
  author = {Du, Yuntao and Wang, Jindong and Feng, Wenjie and Pan, Sinno and Qin, Tao and Xu, Renjun and Wang, Chongjun},
  booktitle = {The 30th ACM International Conference on Information \& Knowledge Management (CIKM)},
  pages = {402--411},
  year = {2021},
  bibtex_show = {true},
  abbr = {CIKM},
  corr = {true},
  selected = {true},
  arxiv = {https://arxiv.org/abs/2108.04443},
  code = {https://github.com/jindongwang/transferlearning/tree/master/code/deep/adarnn},
  pdf = {cikm21-adarnn.pdf},
  special = {Paperdigest most influencial CIKM paper}
}

Visual domain adaptation with manifold embedded distribution alignment

Jindong Wang , Wenjie Feng, Yiqiang Chen, Han Yu, Meiyu Huang, and Philip S Yu

The 26th ACM international conference on Multimedia 2018 | [ PDF Supp Code Poster ]

(600+ citations; 2nd most cited paper in MM’18)

@inproceedings{wang2018visual,
  title = {Visual domain adaptation with manifold embedded distribution alignment},
  author = {Wang, Jindong and Feng, Wenjie and Chen, Yiqiang and Yu, Han and Huang, Meiyu and Yu, Philip S},
  booktitle = {The 26th ACM international conference on Multimedia},
  pages = {402--410},
  year = {2018},
  bibtex_show = {true},
  abbr = {ACMMM},
  code = {https://github.com/jindongwang/transferlearning/tree/master/code/traditional/MEDA},
  pdf = {a11_mm18.pdf},
  supp = {https://www.jianguoyun.com/p/DRuWOFkQjKnsBRjkr2E},
  poster = {poster_mm18.pdf},
  selected = {true},
  special = {600+ citations; 2nd most cited paper in MM'18}
}

Balanced distribution adaptation for transfer learning

Jindong Wang , Yiqiang Chen, Shuji Hao, Wenjie Feng, and Zhiqi Shen

IEEE international conference on data mining (ICDM) 2017 | [ HTML PDF Code ]

(600+ citations; Most cited paper in ICDM’17)

@inproceedings{wang2017balanced,
  title = {Balanced distribution adaptation for transfer learning},
  author = {Wang, Jindong and Chen, Yiqiang and Hao, Shuji and Feng, Wenjie and Shen, Zhiqi},
  booktitle = {IEEE international conference on data mining (ICDM)},
  pages = {1129--1134},
  year = {2017},
  organization = {IEEE},
  bibtex_show = {true},
  abbr = {ICDM},
  code = {https://github.com/jindongwang/transferlearning/tree/master/code/BDA},
  pdf = {a08_icdm17.pdf},
  html = {http://ieeexplore.ieee.org/document/8215613/?part=1},
  selected = {true},
  special = {600+ citations; Most cited paper in ICDM'17}
}