影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
51.78/100
前 7.7%
全站排名 #4,952
发表论文9 篇
平均评分
年均产出3.0 篇/年
Kaijie Zhu
研究方向
Evaluation · Adversarial Robustness
19
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
ICLR 2026Poster
二作15
SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints
ICLR 2026Rejected
22
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
ICLR 2026Rejected
二作16
PromptArmor: An Essential Baseline for Prompt Injection Defenses
ICLR 2026Rejected
二作11
Fourier Minds, Forget Less: Discrete Fourier Transform for Fast and Robust Continual Learning in LLMs
ICLR 2026Withdrawn
28
Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models
NeurIPS 2025Poster
三作21
Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent Approach
NeurIPS 2025Poster
三作11
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
ICML 2025Poster
一作