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
43.44/100
前 12%
全站排名 #7,726
发表论文6 篇
平均评分
年均产出2.0 篇/年
Stephen Bach
研究方向
Language models · Vision-language models · Weakly supervised machine learning · Information extraction · Probabilistic graphical models
13
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
ICLR 2026Poster
二作20
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools
ICLR 2026Rejected
三作13
Crosslingual Reasoning through Test-Time Scaling
ICLR 2026Rejected
10
Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
ICLR 2026Rejected
三作