Zhuo Huang Ph.D. Student Sydney AI Centre School of Computer Science The University of Sydney Address: J12/ 1 Cleveland St, Darlington, NSW 2008, Australia Email: zhuohuang DOT ai AT gmail DOT com

Biography

I am currently a Ph.D. Student at the School of Computer Science, The University of Sydney, feeling fortunate to learn from Prof. Tongliang Liu. Before, I studied Industrial Design at CUG and then jumped to Computer Science at NJUST, advised by Prof. Chen Gong. I was a visiting scholar at USTC and THU in 2022 and 2023, respectively. I hope to achieve general machine intelligence which can tackle various real-world problems. To do that, I focus on OOD Generalization and AI Safety.

Publication

• Improving Non-Transferable Representation Learning by Harnessing Content and Style [Spotlight]
  Z. Hong, Z. Wang, L. Shen, Y. Yao, Z. Huang, S. Chen, C. Yang, M. Gong, T. Liu
  ICLR 2024
  

• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
  Z. Huang, C. Liu, Y. Dong, H. Su, S. Zheng, T. Liu
  arXiv 2023
  

• Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization
  Z. Huang, M. Li, L. Shen, J. Yu, C. Gong, B. Han, T. Liu
  IJCV 2024
  

• FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning
  Z. Huang, L. Shen, J. Yu, B. Han, T. Liu
  NeurIPS 2023
  

• Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization
  Z. Huang*, M. Zhu*, X. Xia, L. Shen, J. Yu, C. Gong, B. Han, B. Du, T. Liu
  CVPR 2023
  

• Harnessing Out-Of-Distribution Examples via Augmenting Content and Style
  Z. Huang, X. Xia, L. Shen, B. Han, M. Gong, C. Gong, T. Liu
  ICLR 2023
  

• Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch
  M. Li, T. Zhou, Z. Huang, J. Yang, J. Yang, C. Gong
  ACM TOMM 2023
  

• They are Not Completely Useless: Towards Recycling Transferable Unlabeled Data for Class-Mismatched Semi-Supervised Learning
  Z. Huang, J. Yang, C. Gong
  IEEE TMM 2022
  

• Universal Semi-Supervised Learning
  Z. Huang, X. Chao, B. Han, J. Yang, C. Gong
  NeurIPS 2021
  

Honors and Awards

• JSAI Distinguished M.S. Thesis, 2022.

• LEAP Fellow, 2022.

• Distinguished Undergraduate Thesis, 2019.

• National Scholarship, 2017.

Academic Services

• Conference Reviewer: ICML, NeurIPS, ICLR, CVPR, IJCAI, AISTATS, UAI, ACM MM, CIKM, CAI, etc.

• Journal Reviewer: TPAMI, TMM, TMLR, MLJ, NEUNET, etc.