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
42.5/100
前 12.7%
全站排名 #8,153
发表论文5 篇
平均评分
年均产出2.5 篇/年
Shojiro Yamabe
研究方向
Deep learning · reinforcement learning · Robustness · Adversarial attack · Large language models · security · model watermarking
13
Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
ICLR 2026Poster
一作18
Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
ICLR 2026Poster
一作16
Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness
ICLR 2026Poster
二作