Scholar
Kaijie Zhu
Google Scholar ID: g75dFLYAAAAJ
University of California, Santa Barbara
Citations & Impact
Citations
5,504
H-index
12
i10-index
13
Publications
20
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - MELON: Indirect Prompt Injection Defense via Masked Re-execution and Tool Comparison, ICML 2025
- - DyVal: Graph-informed Dynamic Evaluation of Large Language Models, ICLR (Spotlight) 2024
- - PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts, CCS LAMPS Workshop 2023
- - Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning, ICCV 2023
- - DyVal 2: Dynamic Evaluation of Large Language Models by Meta Probing Agents, ICML 2024
- - Awards:
- - MELON accepted by ICML 2025
- - Hosting the AAAI 2025 Tutorial on Evaluating Large Language Models: Challenges and Methods with Prof. Jindong Wang, Dr. Linyi Yang, Prof. Yue Feng, and Prof. Yue Zhang
- - Selected to present a talk at the KAUST Rising Stars in AI Symposium 2025
- - PromptRobust accepted by CCS LAMPS Workshop
- - DyVal 2 accepted by ICML 2024
Research Experience
- - Internship at Microsoft
- - Advisors: Prof. Jindong Wang and Prof. Xing Xie
Education
- - Degree: Ph.D. in progress
- - University: University of California, Santa Barbara (UCSB)
- - Advisors: Prof. William Wang and Prof. Wenbo Guo
- - Time: Current
- - Field: Not specified
Background
- - Research Interests: Development of trustworthy AI systems and evaluation of foundation models
- - Advisors: Prof. William Wang and Prof. Wenbo Guo
- - Personal Background: First-year Ph.D. student at UCSB, previously interned at Microsoft, advised by Prof. Jindong Wang and Prof. Xing Xie
- - Hobbies: Playing tennis and hold’em
Miscellany
- - Hobbies: Playing tennis and hold’em
