Scholar
Beier Zhu
Google Scholar ID: jHczmjwAAAAJ
Research Scientist, Nanyang Technological University
Citations & Impact
Citations
962
H-index
10
i10-index
12
Publications
20
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including but not limited to:
- - 'Subject-consistent and pose-diverse text-to-image generation'
- - 'Unsupervised visual chain-of-thought reasoning via preference optimization'
- - 'Distilling parallel gradients for fast ODE solvers of diffusion models'
- - 'Project-probe-aggregate: efficient fine-tuning for group robustness'
- - 'Generalized kullback-leibler divergence loss'
- - 'Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting' etc.
Research Experience
- Currently a Research Fellow in the MReaL Lab at Nanyang Technological University, working with Prof. Hanwang Zhang.
Education
- Obtained a PhD degree from Nanyang Technological University, supported by the prestigious AISG PhD programme; received B.E. and M.E. degrees from Tsinghua University in 2016 and 2019, respectively.
Background
- Currently a Research Fellow in the MReaL Lab at Nanyang Technological University, focusing on developing robust machine learning algorithms with strong theoretical foundations, particularly in imbalanced learning, group robustness, out-of-distribution (OOD) generalization, and fairness. 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.
