Welcome to Rongzhe Wei (魏容哲)’s Personal Website

I’m a fifth-year PhD student in machine learning at Georgia Institute of Technology, advised by Prof. Pan Li. My current research interests include Trustworthy Machine Learning (Machine Unlearning, Privacy, Model Safety), Graph Analysis (Graph Diffusion, Graph Neural Networks), and Large Language Models, Agentic AI (Planning, Decision-making, Search Mechanism).

Prior to that, I received my bachelor’s degree in Honors Math Program from Xi’an Jiaotong University.

Preprints

• [arXiv] The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
  Rongzhe Wei*, Peizhi Niu*, Xinjie Shen*, Tony Tu, Yifan Li, Ruihan Wu, Eli Chien, Pin-yu Chen, Olgica Milenkovic, and Pan Li
  arXiv preprint, 2025 · [PDF] [Project] [Code]

• [ICLR’26 · Under Review] MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
  Yupu Gu, Rongzhe Wei, Andy Zhu, and Pan Li

• [ICLR’24 · PML Workshop] Guarding Multiple Secrets: Enhanced Summary Statistic Privacy for Data Sharing
  Shuaiqi Wang, Rongzhe Wei, Mohsen Ghassemi, Eleonora Kreacic, and Vamsi K. Potluru

Selected Publications

• [NeurIPS’25] Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
  Rongzhe Wei*, Peizhi Niu*, Hans Hao-Hsun Hsu, Ruihan Wu, Haoteng Yin, Mohsen Ghassemi, Yifan Li, Vamsi K. Potluru, Eli Chien, Kamalika Chaudhuri, Olgica Milenkovic, and Pan Li
  Advances in Neural Information Processing Systems · [PDF]

• [NeurIPS’25] Differentially Private Relational Learning with Entity-level Privacy Guarantees
  Yinan Huang*, Haoteng Yin*, Eli Chien, Rongzhe Wei, and Pan Li
  Advances in Neural Information Processing Systems · [PDF]

• [ICML’25] Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning
  Rongzhe Wei, Mufei Li, Mohsen Ghassemi, Eleonora Kreacic, Yifan Li, Xiang Yue, Bo Li, Vamsi K. Potluru, Pan Li, and Eli Chien
  International Conference on Machine Learning · [PDF]

• [ICML’25] Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models
  Haoyu Wang, Shikun Liu, Rongzhe Wei, and Pan Li
  International Conference on Machine Learning · [PDF]

• [COLM’25] Privately Learning from Graphs with Applications in Fine-tuning Large Language Models
  Haoteng Yin, Rongzhe Wei, Eli Chien, and Pan Li
  Conference on Language Modeling · [PDF]

• [NeurIPS’24] Differentially Private Graph Diffusion with Applications in Personalized PageRanks
  Rongzhe Wei, Eli Chien, and Pan Li
  Advances in Neural Information Processing Systems · [PDF]

• [TMLR’24 → ICLR’25] On the Inherent Privacy Properties of Discrete Denoising Diffusion Models
  Rongzhe Wei, Eleonora Kreačić, Haoyu Wang, Haoteng Yin, Eli Chien, Vamsi K. Potluru, and Pan Li
  Transactions on Machine Learning Research · Selected to ICLR’25 Poster · [PDF]

• [WWW’24] Learning Scalable Structural Link Representations with Bloom Signatures
  Tianyi Zhang*, Haoteng Yin*, Rongzhe Wei, Pan Li, and Anshumali Shrivastava
  Proceedings of the ACM Web Conference · [PDF]

• [TKDE’24] SLA²P: Self-supervised Anomaly Detection with Adversarial Perturbation
  Yizhou Wang, Can Qin, Rongzhe Wei, Yi Xu, Yue Bai, and Yun Fu
  IEEE Transactions on Knowledge and Data Engineering · [PDF]

• [NeurIPS’22] Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective
  Rongzhe Wei, Haoteng Yin, Junteng Jia, Austin R. Benson, and Pan Li
  Advances in Neural Information Processing Systems · [PDF]

Education

• Georgia Institute of Technology (GaTech) (Present)
  Ph.D. in Machine Learning (ECE Department)
  Supervisor: Prof. Pan Li

• Xi’an Jiaotong University (XJTU) (2017–2021)
  B.S. in Mathematics and Applied Mathematics (National Honors Program - Qian Xuesen College)
  GPA: 3.87/4.00

• Georgia Institute of Technology (GaTech) (2020 Spring)
  Visiting Honors Student Program (School of Mathematics)

• University of Alberta (2017 Summer)
  International Undergraduate Summer Enrichment Program in Mathematics

Professional Services

• Conference Reviewer: NeurIPS’22-25, ICML’24-25, ICLR’25-26, AISTATS’23-24, ISIT’25, AAAI’24, LoG’22-24
• Journal Reviewer: Computers and Mathematics with Applications, TMLR
• Graduate Teaching Assistant:
  • ECE 6720 Convex Optimization (Graduate Level)
  • ECE 3077 Introduction to Probability and Statistics for ECEs
  • ECE 8003 Conversational AI (Graduate Level)

Industrial Experiences

• Amazon — Seattle, WA
  AI Research Intern
  May 2025 – August 2025
  • Project: Reflection and Exploration-based LLM Action Planning
• JP Morgan Chase & Co. — Manhattan, NYC, NY
  AI Research Intern
  June 2023 – August 2023
  • Project: A General Framework for Graph Data Generation Control via Margin Relaxed Schrodinger Bridges
  • Mentors: Eleonora Kreačić and Vamsi K Potluru

Selected Honors & Scholarship

• Georgia Tech CSIP Outstanding Research Award · 2025
• Lambda’s Research Grant · 2025
• OpenAI API Researcher Access Program Grant · 2025
• Travel Award · NeurIPS 2022
• Student Award · IEEE International Conference on BigData 2019
• The First Prize of “Zhufeng” Scholarship
  (Ministry of Education, Pilot Scheme of Top-notch Talent Cultivation in Basic Disciplines)
• Outstanding Student Award · Xi’an Jiaotong University
• First-class Scholarship · Xi’an Jiaotong University

Technical Skills

• Languages: Chinese (native), English
• Programming Languages: Python, C#, Matlab, C, SQL, HTML
• Piano: Band 9 out of 9 (Central Conservatory of Music) achieved at the age of 12, and won the 5th China Outstanding Talents Art Festival National Competition (Gold Award)