About Me

I am currently a Research Scientist in ByteDance AI-Lab. Before joining ByteDance, I received my Ph.D degree in Mathematics from The Hong Kong University of Science and Technology (HKUST), supervised by Prof. Tong Zhang. Before that, I obtained my Bachelor degree in Electronic Engineering from Tsinghua University.

I am interested in broader topics in machine learning, including adversarial robustness and large language models.

Publications

• Fast Adversarial Training with Adaptive Step Size
  Zhichao Huang, Yanbo Fan, Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang
  Transcation on Image Processing (TIP)
• Towards Stable and Efficient Adversarial Training against $\ell_1$ Bounded Adversarial Attacks
  Yulun Jiang, Chen Liu, Zhichao Huang, Mathieu Salzmann, Sabine Süsstrunk
  Fortieth International Conference on Machine Learning (ICML 2023)
  [code]
• Black-Box Prompt Learning for Pre-trained Language Models
  Shizhe Diao, Zhichao Huang, Ruijia Xu, Xuechun Li, Yong Lin, Xiao Zhou, Tong Zhang
  Transactions on Machine Learning Research (TMLR)
  [code]
• On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
  Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine Süsstrunk
• Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling
  Zhichao Huang, Xintong Han, Jia Xu, Tong Zhang
  2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2021)
  [code][video]
• Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems
  Luo Luo, Haishan Ye, Zhichao Huang, Tong Zhang
  34th Conference on Neural Information Processing Systems (NeurIPS 2020)
• Black-box Adversarial Attack with Transferable Model-Based Embedding
  Zhichao Huang, Tong Zhang
  Eighth International Conference on Learning Representations (ICLR 2020)
  [code]
• Hessian-Aware Zeroth-Order Optimization for Black-box Adversarial Attack
  Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang
  NeurIPS Workshop on Beyond First Order Methods in ML, 2019
• Enhancing CNN Incremental Learning Capability with an Expanded Network
  Shanshan Cai*, Zhuwei Xu*, Zhichao Huang*, Yueru Chen, C.-C. Jay Kuo
  2018 IEEE International Conference on Multimedia and Expo (ICME 2018) (*equal contribution)

Preprints

• Speech Translation with Large Language Models: An Industrial Practice
  Zhichao Huang, Rong Ye, Tom Ko, Qianqian Dong, Shanbo Cheng, Mingxuan Wang, Hang Li
  [demo]
• RepCodec: A Speech Representation Codec for Speech Tokenization
  Zhichao Huang*, Chutong Meng*, Tom Ko
  [code]
• CorrAttack: Black-box Adversarial Attack with Structured Search
  Zhichao Huang*, Yaowei Huang*, Tong Zhang (*equal contribution)

Experiences

• Research Intern, Tencent AI Lab, Shenzhen, China
  Topic: Adversarial Examples
  Mentor: Yanbo Fan
  Mar 2021 - Nov 2021
• Research Intern, Huya Inc, Guangzhou, China
  Topic: Human Motion Transfer
  Mentor: Jia Xu
  Jun 2019 - Aug 2019
• Research Intern, Sensetime Group Limited, Beijing, China
  Topic: Multitask Semantic Segmentation in Autonomous Driving
  Mentor: Guangliang Cheng
  Dec 2017 - Jun 2018
• Research Assistant, University of Southern California, Los Angeles, USA
  Topic: Incremental Learning in CNN
  Advisor: C.-C. Jay Kuo
  Jun 2017 - Aug 2017

Teaching

• MATH 1014 - Calculus II (Spring 2019)
• MATH 1013 - Calculus IB (Fall 2019)
• MATH 2011 - Introduction to Multivariable Calculus (Spring 2020, Spring 2021)
• MATH 2111 - Matrix Algebra and Applications (Fall 2020, Fall 2021)
• MATH 2011 - Introduction to Multivariable Calculus (Spring 2021)

Awards

• Best TA Teaching Award, 2020 - 2021
• HKUST Postgraduate Studentship, 2018-2022

Academic Service

• Reviewer of ICML, NeurIPS, ICLR, T-PAMI, IJCV, SIMODS