CV

Ph.D. Student in Computer Science

Michigan State University, USA

• Trustworthy Machine Learning
  • Model Robustness (Adversarial Robustness, Backdoor Attacks, Out-of-Distribution, etc.)
  • Model Fairness
  • Machine Unlearning (Copyright infringement, Harmful Content Removal)
• Scalable Machine Learning
  • Efficient Model (Model Pruning, Mixture-of-Expert, On-Device Training)
  • Efficient Data (Data Distillation, Coreset Selection)
• Foundation Algorithm Development
  • Bi-Level Optimization
  • Zeroth-Order Optimization
  • Invariant Risk Minimization
  • Distribution Machine Learning

B.Eng. in Mechanical Engineering

Huazhong University of Science and Technology, China

Research Scientist Intern

Cisco Research

• Investigate efficient and effective machine unlearning algorithms for foundation models, including Large Language Models (LLMs), Diffusion Models (DMs), and Mixture-of-Experts (MoEs).

Applied Scientist Intern

Amazon AWS

• Investigate the in-context learning for vision generative models, including its design, training, and generalization ability.

Research Internship

JD AI Research

• Develop algorithms to enhance the robustness and the fairness of the AI algorithms, such as facial recognition, ORC, object detection. Implement and release the new designed algorithms to the JD corperation for intern use or as part of the commercial APIs.

• 2024 MLCommons ML and Systems Rising Stars sponsored by Nvidia

• AAAI 2023 Travel Award
• NeurIPS Scholar Award
• NeurIPS Top Reviewer
• CVPR 2023 Outstanding Reviewer

• Best Paper Runner-up Awards, UAI 2022
• NeurIPS Scholar Award
• NeurIPS Top Reviewer
• ICML 2022 Travel Grant Award

• National Scholarship

• National Scholarship