Zhiyu Xue
Scholar

Zhiyu Xue

Google Scholar ID: t72rUpAAAAAJ
University of California, Santa Barbara
few-shot learninginterpretability
Google Scholar↗
Citations & Impact
All-time
Citations
120
 
H-index
7
 
i10-index
6
 
Publications
17
 
Co-authors
15
list available
Contact
No contact links provided.
Publications
6 items
Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
2026
Cited
0
Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment
2026
Cited
0
On the Convergence of Moral Self-Correction in Large Language Models
2025
Cited
0
Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations
2025
Cited
0
Smaller Large Language Models Can Do Moral Self-Correction
arXiv.org · 2024
Cited
0
Communication-Efficient and Tensorized Federated Fine-Tuning of Large Language Models
arXiv.org · 2024
Cited
3
Resume (English only)
Co-authors
15 total
Kristen Marie Johnson
Kristen Marie Johnson
Michigan State University
Xitong Zhang
Xitong Zhang
Qualcomm
Rongrong Wang
Rongrong Wang
Michigan State University
Lixin Duan
Lixin Duan
Data Intelligence Group (DIG) @ UESTC
Ramtin Pedarsani
Ramtin Pedarsani
Associate Professor, Electrical and Computer Engineering, UC Santa Barbara
Yao Qin
Yao Qin
UCSB & Google DeepMind
Wen Li
Wen Li
Data Intelligence Group, UESTC
Lin Chen
Lin Chen
Chief Scientist @ Wyze