Rongzhe Wei

PhD student@Georgia Institute of Technology·美国·OpenReview

研究方向

Large Language Models · Agentic AI (Planning · Decision-making · Search Mechanism) · Trustworthy Machine Learning (Machine Unlearning · Privacy · Model Safety) · Graph Analysis (Graph Diffusion · Graph Neural Networks)

5.0

MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs

ICLR 2026Poster

二作

6.8

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

NeurIPS 2025Poster

一作

6.4

Differentially Private Relational Learning with Entity-level Privacy Guarantees

NeurIPS 2025Poster

6.3

Privately Learning from Graphs with Applications in Fine-tuning Large Language Models

COLM 2025Poster

二作

6.3

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

ICML 2025Poster

一作

5.7

Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning

ICLR 2025Rejected

一作

5.5

Generalization Principles for Inference over Text-Attributed Graphs with Large Language Models

ICML 2025Poster

三作

4.3

Privately Learning from Graphs with Applications in Fine-tuning Large Pretrained Models

合作者 (20)