I’m currently a Research Fellow at Nanyang Technological University, working with Prof. Hanwang Zhang.

I obtained my PhD degree from Nanyang Technological University advised by Prof. Hanwang Zhang. Prior to the PhD, I received B.E. and M.E. degree from Tsinghua University in 2016 and 2019.

Research Topics

Theory: I develop robust machine learning algorithms, with interests in long-tailed learning, group robustness, OOD generalization, and fairness.

Application: I’m interested in understanding and applying large multimodal models, e.g., MLLMs, VLMs, and Stable Diffusion, to downstream tasks.

Publications

(* denotes equal contribution. ^ denotes corresponding author)

• Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness.
  Beier Zhu, Jiequan Cui, Hanwang Zhang, Chi Zhang
  Main Track Highlight, Conference on Computer Vision and Pattern Recognition, CVPR 2025.

• Robust Fine-tuning of Zero-shot Models via Variance Reduction.
  Beier Zhu, Jiequan Cui, Hanwang Zhang
  Main Track, Conference on Neural Information Processing Systems, NeurIPS 2024

• Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting.
  Xingyu Zhu*, Beier Zhu*, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang
  Main Track Spotlight, Conference on Neural Information Processing Systems, NeurIPS 2024.

• Selective Vision-Language Subspace Projection for Few-shot CLIP.
  Xingyu Zhu*, Beier Zhu*, Yi Tan, Shuo Wang, Yanbin Hao, Hanwang Zhang
  Main Track Oral, Conference on Neural Information Processing Systems. NeurIPS 2023.

• Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models.
  Beier Zhu, Kaihua Tang, Qianru Sun, Hanwang Zhang
  Main Track, Conference on Neural Information Processing Systems. NeurIPS 2023.
  paper code

• Prompt-aligned Gradient for Prompt Tuning.
  Beier Zhu, Yulei Niu, Yucheng Han, Yue Wu, Hanwang Zhang.
  Main Track, IEEE International Conference on Computer Vision. ICCV 2023.
  paper code

• Debiased Fine-Tuning for Vision-language Models by Prompt Regularization.
  Beier Zhu, Yulei Niu, Saeil Lee, Minhoe Hur, Hanwang Zhang.
  Main Track Oral, AAAI Conference on Artificial Intelligence. AAAI 2023.
  paper code

• Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning.
  Chen Chen, Yuchen Hu, Qiang Zhang, Heqing Zou, Beier Zhu, Eng Siong Chng.
  Main Track Oral, AAAI Conference on Artificial Intelligence. AAAI 2023.
  paper

• Cross-Domain Empirical Risk Minimization for Unbiased Long-Tailed Classification.
  Beier Zhu, Yulei Niu, Xian-Sheng Hua, Hanwang Zhang.
  Main Track Oral, AAAI Conference on Artificial Intelligence. AAAI 2022.
  paper code

• Structure-Coherent Deep Feature Learning for Robust Face Alignment.
  Chunze Lin*, Beier Zhu*, Quan Wang, Renjie Liao, Chen Qian, Jiwen Lu, Jie Zhou.
  IEEE Transactions on Image Processing. TIP 2021.
  paper code

• Fault Location for Radial Distribution Network via Topology and Reclosure-Generating Traveling Waves.
  Shenxing Shi, Beier Zhu^, Aoyu Lei, Xinzhou Dong.
  IEEE Transactions on Smart Grid. TSG 2019.
  paper

• Fault Classification for Transmission Lines Based on Group Sparse Representation.
  Shenxing Shi, Beier Zhu^, Sohrab Mirsaeidi, Xinzhou Dong.
  IEEE Transactions on Smart Grid. TSG 2018.
  paper

• Polygonal Region Detection.
  Beier Zhu, Rui Zhang.
  US Patent, 2022.