Scholar
Rongzhe Wei
Google Scholar ID: FTHUBdAAAAAJ
Georgia Institute of Technology
LLM Trustworthy
Graph Analysis
Privacy
Unlearning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
131
H-index
6
i10-index
4
Publications
17
Co-authors
7
list available
Contact
Email
rongzhe.wei@gatech.edu
CV
Open ↗
GitHub
Open ↗
Publications
15 items
SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents
2026
Cited
0
Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths
2026
Cited
0
What Must a World Model Distinguish for Planning?
2026
Cited
0
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
2026
Cited
0
Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
2026
Cited
0
MoEEdit: Efficient and Routing-Stable Knowledge Editing for Mixture-of-Experts LLMs
2026
Cited
0
GRIP: Algorithm-Agnostic Machine Unlearning for Mixture-of-Experts via Geometric Router Constraints
2026
Cited
0
A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
2025
Cited
0
Load more
Co-authors
6 total
Pan Li
Georgia Institute of Technology, Purdue University
Haoteng YIN
Purdue University
Y. Raymond Fu
NEU, COE Distinguished Professor; MAE, FNAI, FAAAS, FIEEE, FAAAI
Yizhou Wang
Northeastern University
Can Qin
Salesforce
Huan He
Yale University School of Medicine, Department of Biomedical Informatics & Data Science
