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
-/100
发表论文4 篇
平均评分
年均产出4.0 篇/年
29
A$^2$RM: Adversarial-Augmented Reward Model
ICLR 2026Rejected
三作5
SafeEvalAgent: Toward Agentic and Self-Evolving Safety Evaluation of LLMs
ICLR 2026Withdrawn
二作5
FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
ICLR 2026Withdrawn
一作5
Imperceptible Jailbreaking against Large Language Models
ICLR 2026Withdrawn