Chenhang Cui
Scholar

Chenhang Cui

Google Scholar ID: V5X1gdAAAAAJ
National University of Singapore
AI AlignmentFoundation ModelsAI safety
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,125
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
0
 
Contact
Emailchenhangcui@gmail.comTwitterOpen ↗GitHubOpen ↗
Publications
11 items
Do LLMs and VLMs Share Neurons for Inference? Evidence and Mechanisms of Cross-Modal Transfer
2026
Cited
0
Transport and Merge: Cross-Architecture Merging for Large Language Models
2026
Cited
0
Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment
2026
Cited
0
Self-Guard: Defending Large Reasoning Models via enhanced self-reflection
2026
Cited
0
Improving Alignment in LVLMs with Debiased Self-Judgment
2025
Cited
0
VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization
2025
Cited
0
IKOD: Mitigating Visual Attention Degradation in Large Vision-Language Models
2025
Cited
0
DTPA: Dynamic Token-level Prefix Augmentation for Controllable Text Generation
2025
Cited
0
Resume (English only)
Education
  • Undergraduate student majoring in Computer Science and Technology at Yingcai Honors College, University of Electronic Science and Technology of China (UESTC).
Background
  • Research Interests: Alignment in AI, Large Multimodal Models, and Multimodal representation learning. Major: Computer Science and Technology.
Co-authors
0 total
Co-authors: 0 (list not available)