Kaijie Zhu
kaijiezhu@ucsb.edu
CA, US
I’m a second-year Ph.D student at UCSB, fortunately advised by Prof. William Wang and Prof. Wenbo Guo. I am currently a part-time research intern at AMD Research. Previously, I have interned at Microsoft Research (Redmond, WA) and Microsoft Research Asia, advised by Prof. Jindong Wang and Prof. Xing Xie.
My research interests span evaluating, training, and securing AI agent systems. In my spare time, I love playing tennis and Texas hold’em.
- Agent for Tool Use: benchmarking (DevOps-Gym, ICLR 2026), defending indirect prompt injection (MELON, ICML 2025)
- Dynamic Evaluation of LLMs: DyVal ICLR’24 Spotlight, DyVal 2 ICML’24, PromptBench (JMLR MLOSS)
- Adversarial Robustness: RiFT ICCV’23, PromptRobust CCS’24 LAMPS
news
| Jan 26, 2026 | DevOps-Gym is accepted by ICLR 2026. |
|---|---|
| May 1, 2025 | MELON is accepted by ICML 2025. |
| Feb 25, 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. |
| Jan 20, 2025 | Selected to present a talk at the KAUST Rising Stars in AI Symposium 2025. |
| Aug 17, 2024 | PromptRobust is accepted by CCS LAMPS Workshop. |
selected publications
-
- PromptBench: A Unified Library for Evaluation of Large Language ModelsJMLR MLOSS, 2024
-
MELON: Indirect Prompt Injection Defense via Masked Re-execution and Tool ComparisonICML, 2025 -
DyVal: Graph-informed Dynamic Evaluation of Large Language ModelsICLR (Spotlight), 2024 -
PromptBench: Towards Evaluating the Robustness of Large Language Models on Adversarial PromptsCCS LAMPS Workshop, 2023 -
Improving Generalization of Adversarial Training via Robust Critical Fine-TuningICCV, 2023 -
DyVal 2: Dynamic Evaluation of Large Language Models by Meta Probing AgentsICML, 2024
