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
10.6/100
超过 32.9%
全站排名 #43,198
发表论文4 篇
平均评分
年均产出2.0 篇/年
12
Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR
ICLR 2026Poster
31
Learning to Reward: A Contextual Bandit Framework for Distributional Reward Policy Optimization
ICLR 2026Rejected
一作5
Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle
ICLR 2026Withdrawn
二作