Zherui Li
Scholar

Zherui Li

Google Scholar ID: qcJ5riMAAAAJ
Beijing University of Posts and Telecommunications
Large Language ModelTrustworthy AILLM-based Agent
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
71
 
H-index
3
 
i10-index
3
 
Publications
5
 
Co-authors
0
 
Contact
No contact links provided.
Publications
8 items
Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
2026
Cited
0
Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
2026
Cited
0
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
2025
Cited
0
LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space
2025
Cited
0
Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation
2025
Cited
0
Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
2025
Cited
0
CORBA: Contagious Recursive Blocking Attacks on Multi-Agent Systems Based on Large Language Models
2025
Cited
0
Reinforced Lifelong Editing for Language Models
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)