About me

I am currently pursuing my Ph.D. in the Department of Computer Science and Engineering (CSE) at the Chinese University of Hong Kong, under the supervision of Prof. James Cheng and Prof. Wei Meng. Additionally, I collaborate closely with Prof. Bo Han. In 2021, I obtained my bachelor’s degree at the School of Data Science (SDS), Fudan University.

My research focuses on the fundamental principles of modern machine learning and its applications in real-world scenarios. Specifically, I am working on exploring representation learning and generalization methods through the lenses of robustness and inductive bias.

I am open to potential collaborations, visiting opportunities, and discussions on new research directions. Additionally, I am enthusiastic about collaborating with junior students. If you are interested, please feel free to contact me!

Email: bhxie21 [at] cse.cuhk.edu.hk

Selected Publications

* indicates equal contributions.

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Binghui Xie, Yatao Bian, Kaiwen Zhou, Yongqiang Chen, Peilin Zhao, Bo Han, Wei Meng, James Cheng.
In International Conference on Learning Representations (ICLR), 2024. [paper]

Enhancing Evolving Domain Generalization through Dynamic Latent Representations
Binghui Xie, Yongqiang Chen, Jiaqi Wang, Kaiwen Zhou, Bo Han, Wei Meng, James Cheng.
In AAAI Conference on Artificial Intelligence (AAAI), 2024. [paper] Oral presentation (~2.0%)

Understanding and Improving Composite Bayesian Optimization
Kaiwen Zhou*, Binghui Xie*, Junlong Lyu, Zhitang Chen.
In AAAI Workshop on Learnable Optimization (AAAI LEANOPT), 2024.

Positional Information Matters for Invariant In-Context Learning: A Case Study of Simple Function Classes
Yongqiang Chen, Binghui Xie, Kaiwen Zhou, Bo Han, Yatao Bian, James Cheng.
Preprint [paper]

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?
Yongqiang Chen, Yatao Bian, Kaiwen Zhou, Binghui Xie, Bo Han, James Cheng
In Advances in Neural Information Processing Systems (NeurIPS), 2023. [paper]

An Adaptive Incremental Gradient Method With Support for Non-Euclidean Norms
Binghui Xie*, Chenhan Jin*, Kaiwen Zhou, James Cheng, Wei Meng.
Preprint [paper]

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in OOD Generalization
Yongqiang Chen, Kaiwen Zhou, Yatao Bian, Binghui Xie, Bingzhe Wu, Peilin Zhao, Bo Han, James Cheng and others.
In International Conference on Learning Representations (ICLR), 2023. [paper]

Academic Services and Awards

Conference: ICML(22/23/24), AISTATS(22/23/24), NeurIPS(23), ICLR(24), CVPR(24), IJCAI(24), KDD(24)
Journal: TMLR, Neural Networks, TNNLS, JAIR
Conference Awards: AAAI-24 Scholarship

Internship and Visiting

August 2023 - January 2024: Research Intern at Noah’s Ark Lab.
February 2023 - Now: Research Assistant at TMLR Group, HKBU.
September 2022 - February 2023: Research Intern at Tencent AI Lab.
Octorber 2020 - April 2021: Research Assistant at Husky Lab, CUHK.
Octorber 2019 - June 2020: Research Intern at AWS AI Lab.
June 2019 - September 2019: Research Assistant at CCVL Group, JHU.