Scholar
Yuhui Wang
Google Scholar ID: eJgbw-oAAAAJ
Stony Brook University
Prognosis and health management
Large language model
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
67
H-index
5
i10-index
4
Publications
9
Co-authors
9
list available
Contact
No contact links provided.
Publications
2 items
AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks
2026
Cited
0
RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models
2026
Cited
0
Resume (English only)
Academic Achievements
[{'Title': 'Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models', 'Authors': 'Yuhui Wang, Changjiang Li, Guangke Chen, et al.', 'PublicationDate': 'September 2025'}, {'Title': 'Self-Improving Model Steering', 'Authors': 'Rongyi Zhu, Yuhui Wang, Tanqiu Jiang, et al.', 'PublicationDate': 'July 2025'}, {'Title': 'Self-Destructive Language Model', 'Authors': 'Yuhui Wang, Rongyi Zhu, Ting Wang', 'PublicationDate': 'May 2025'}, {'Title': 'AutoRAN: Weak-to-Strong Jailbreaking of Large Reasoning Models', 'Authors': 'Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, et al.', 'PublicationDate': 'May 2025'}, {'Title': 'GraphRAG under Fire', 'Authors': 'Jiacheng Liang, Yuhui Wang, Changjiang Li, et al.', 'PublicationDate': 'January 2025'}]
Background
Research interests include the field of computer science, particularly the security and improvement methods of large reasoning models.
Co-authors
9 total
Ting Wang
Alps Lab
Jiacheng Liang
Stony Brook University
Tanqiu Jiang
Stony Brook University
Changjiang Li
Stony Brook
Andi Wang
University of Wisconsin-Madison
Co-author 6
Co-author 7
Neil Zhenqiang Gong
Associate Professor, Duke University
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up