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
24.31/100
前 32.5%
全站排名 #20,906
发表论文4 篇
平均评分
年均产出4.0 篇/年
13
Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
ICLR 2026Poster
一作13
Crosslingual Reasoning through Test-Time Scaling
ICLR 2026Rejected
一作10
Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models
ICLR 2026Rejected
二作6
Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling
ICLR 2026Withdrawn