Beier Zhu

Research Fellow in Robust Machine Learning,
Nanyang Technological University. Curriculum Vitae

Experience: I’m Beier Zhu (朱贝尔), currently a Research Fellow in the MReaL Lab at Nanyang Technological University, working with Prof. Hanwang Zhang. I obtained my PhD degree from Nanyang Technological University, supported by the prestigious AISG PhD programme. Prior to that, I received my B.E. and M.E. degrees from Tsinghua University in 2016 and 2019, respectively.

Research: My research focuses on developing robust machine learning algorithms with strong theoretical foundations, with particular interests in imbalanced learning, group robustness, out-of-distribution (OOD) generalization, and fairness. On the application side, I am also interested in understanding and leveraging large multimodal models—such as Multimodal Large Language Models (MLLMs), Vision-Language Models (VLMs), and Stable Diffusion—for solving downstream tasks.

Selected Publications

(First, second, and corresponding author papers; * and ^ denote equal contribution and corresponding authorship.)

2025

arXiv

Subject-consistent and pose-diverse text-to-image generation Application: Diffusion Generation

Zhanxin Gao, Beier Zhu, Liang Yao, and 2 more authors

arXiv Bib Video Code PROJECT

@unpublished{gao2025subject,
  title = {Subject-consistent and pose-diverse text-to-image generation},
  author = {Gao, Zhanxin and Zhu, Beier and Yao, Liang and Yang, Jian and Tai, Ying},
  year = {2025},
  projectpage = {https://zhanxin-gao.github.io/CoDi/},
}

ICCV

Unsupervised visual chain-of-thought reasoning via preference optimization Application: Visual Reasoning

Kesen Zhao, Beier Zhu^{^}, Qianru Sun, and 1 more author

In International Conference on Computer Vision

arXiv Bib Code PROJECT

@inproceedings{zhao2025unsupervised,
  title = {Unsupervised visual chain-of-thought reasoning via preference optimization},
  author = {Zhao, Kesen and Zhu, Beier and Sun, Qianru and Zhang, Hanwang},
  booktitle = {International Conference on Computer Vision},
  year = {2025},
  projectpage = {https://kesenzhao.github.io/my_project/projects/UV-CoT.html}
}

ICCV

Distilling parallel gradients for fast ODE solvers of diffusion models Application: Diffusion Generation

Beier Zhu^*, Ruoyu Wang^*, Tong Zhao, and 2 more authors

In International Conference on Computer Vision

arXiv Bib Code

@inproceedings{zhu2025distilling,
  title = {Distilling parallel gradients for fast ODE solvers of diffusion models},
  author = {Zhu, Beier and Wang, Ruoyu and Zhao, Tong and Zhang, Hanwang and Zhang, Chi},
  booktitle = {International Conference on Computer Vision},
  year = {2025},
}

CVPR

Project-probe-aggregate: efficient fine-tuning for group robustness Theory: Group Robustness

Beier Zhu, Jiequan Cui, Hanwang Zhang, and 1 more author

In Computer Vision and Pattern Recognition Conference

Highlight

arXiv Bib Poster

@inproceedings{zhu2025project,
  title = {Project-probe-aggregate: efficient fine-tuning for group robustness},
  author = {Zhu, Beier and Cui, Jiequan and Zhang, Hanwang and Zhang, Chi},
  booktitle = {Computer Vision and Pattern Recognition Conference},
  year = {2025},
}

arXiv

Generalized kullback-leibler divergence loss Theory: Knowledge Distillation

Jiequan Cui, Beier Zhu, Qingshan Xu, and 5 more authors

arXiv Bib Code

@unpublished{cui2025generalized,
  title = {Generalized kullback-leibler divergence loss},
  author = {Cui, Jiequan and Zhu, Beier and Xu, Qingshan and Tian, Zhuotao and Qi, Xiaojuan and Yu, Bei and Zhang, Hanwang and Hong, Richang},
  year = {2025},
}

2024

Thesis

Towards unbiased, accurate and robust fine-tuning of zero-shot vision models

Zhu Beier

PDF

NeurIPS

Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting Theory: Imbalanced Learning

Xingyu Zhu^*, Beier Zhu^*, Yi Tan, and 3 more authors

In Advances in Neural Information Processing Systems

Spotlight

arXiv Bib Code Poster

@inproceedings{zhu2024enhancing,
  title = {Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting},
  author = {Zhu, Xingyu and Zhu, Beier and Tan, Yi and Wang, Shuo and Hao, Yanbin and Zhang, Hanwang},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024}
}

NeurIPS

Robust fine-tuning of zero-shot models via variance reduction Theory: OOD Generalization

Beier Zhu, Jiequan Cui, and Hanwang Zhang

In Advances in Neural Information Processing Systems

arXiv Bib Code Poster

@inproceedings{zhu2024robust,
  title = {Robust fine-tuning of zero-shot models via variance reduction},
  author = {Zhu, Beier and Cui, Jiequan and Zhang, Hanwang},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2024}
}

Selective vision-language subspace projection for few-shot CLIP Application: VLM Adaptation

Xingyu Zhu^*, Beier Zhu^*, Yi Tan, and 3 more authors

In ACM International Conference on Multimedia

Oral

arXiv Bib Code

@inproceedings{zhu2024selective,
  title = {Selective vision-language subspace projection for few-shot CLIP},
  author = {Zhu, Xingyu and Zhu, Beier and Tan, Yi and Wang, Shuo and Hao, Yanbin and Zhang, Hanwang},
  booktitle = {ACM International Conference on Multimedia},
  year = {2024},
}

CVPR

Classes are not equal: An empirical study on image recognition fairness Application: Classification Fairness

Jiequan Cui, Beier Zhu, Xin Wen, and 3 more authors

In Computer Vision and Pattern Recognition Conference

arXiv Bib Code

@inproceedings{cui2024classes,
  title = {Classes are not equal: An empirical study on image recognition fairness},
  author = {Cui, Jiequan and Zhu, Beier and Wen, Xin and Qi, Xiaojuan and Yu, Bei and Zhang, Hanwang},
  booktitle = {Computer Vision and Pattern Recognition Conference},
  year = {2024},
}

2023

NeurIPS

Generalized logit adjustment: Calibrating fine-tuned models by removing label bias in foundation models Theory: Imbalanced Learning

Beier Zhu, Kaihua Tang, Qianru Sun, and 1 more author

In Advances in Neural Information Processing Systems

arXiv Bib Code

@inproceedings{zhu2023generalized,
  title = {Generalized logit adjustment: Calibrating fine-tuned models by removing label bias in foundation models},
  author = {Zhu, Beier and Tang, Kaihua and Sun, Qianru and Zhang, Hanwang},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2023},
}

AAAI

Debiased fine-tuning for vision-language models by prompt regularization Application: VLM Adaptation

Beier Zhu, Yulei Niu, Saeil Lee, and 2 more authors

In AAAI Conference on Artificial Intelligence

Oral

arXiv Bib Code

@inproceedings{zhu2023debiased,
  title = {Debiased fine-tuning for vision-language models by prompt regularization},
  author = {Zhu, Beier and Niu, Yulei and Lee, Saeil and Hur, Minhoe and Zhang, Hanwang},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2023}
}

ICCV

Prompt-aligned gradient for prompt tuning Application: VLM Adaptation

Beier Zhu, Yulei Niu, Yucheng Han, and 2 more authors

In International Conference on Computer Vision

arXiv Bib Code

@inproceedings{zhu2023prompt,
  title = {Prompt-aligned gradient for prompt tuning},
  author = {Zhu, Beier and Niu, Yulei and Han, Yucheng and Wu, Yue and Zhang, Hanwang},
  booktitle = {International Conference on Computer Vision},
  year = {2023},
}

2022

AAAI

Cross-domain empirical risk minimization for unbiased long-tailed classification Theory: Imbalanced Learning

Beier Zhu, Yulei Niu, Xian-Sheng Hua, and 1 more author

In Proceedings of the AAAI conference on artificial intelligence

Oral

arXiv Bib Code

@inproceedings{zhu2022cross,
  title = {Cross-domain empirical risk minimization for unbiased long-tailed classification},
  author = {Zhu, Beier and Niu, Yulei and Hua, Xian-Sheng and Zhang, Hanwang},
  booktitle = {Proceedings of the AAAI conference on artificial intelligence},
  year = {2022}
}

2021

TIP

Structure-coherent deep feature learning for robust face alignment Application: Face Alignment

Chunze Lin^*, Beier Zhu^*, Quan Wang, and 4 more authors

IEEE Transactions on Image Processing

2019

TSG

Fault location for radial distribution network via topology and reclosure-generating traveling waves Application: Power System

Shenxing Shi, Beier Zhu^{^}, Aoyu Lei, and 1 more author

IEEE Transactions on Smart Grid

2018

TSG

Fault classification for transmission lines based on group sparse representation Application: Power System

Shenxing Shi, Beier Zhu^{^}, Sohrab Mirsaeidi, and 1 more author

IEEE Transactions on Smart Grid