Zhexin Zhang
Scholar

Zhexin Zhang

Google Scholar ID: I-Cn8gkAAAAJ
Tsinghua University, CoAI Group
NLPAI Safety & Alignment
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,152
 
H-index
13
 
i10-index
14
 
Publications
20
 
Co-authors
0
 
Contact
Emailzx-zhang22@mails.tsinghua.edu.cnCVOpen ↗TwitterOpen ↗GitHubOpen ↗
Publications
20 items
From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
2026
Cited
0
RUBAS: Rubric-Based Reinforcement Learning for Agent Safety
2026
Cited
0
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
2026
Cited
0
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
2026
Cited
0
MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization
arXiv.org · 2026
Cited
0
"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
2025
Cited
0
Vector sketch animation generation with differentialable motion trajectories
2025
Cited
0
When Smiley Turns Hostile: Interpreting How Emojis Trigger LLMs' Toxicity
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)