confidence-adaptive

CADENCE 提出了一种置信度自适应的双专家网络，用于实现快速且准确的时间序列分类，是一篇 arXiv 上的学术预印本。

CAT introduces a framework that leverages model self-certainty signals to autonomously adjust reasoning length based on problem difficulty, reducing overthinking and improving inference efficiency for large reasoning models.

Proposes Confidence-Aware SwiGLU (κ-SwiGLU) that adjusts expert gate sharpness in Mixture-of-Experts models based on token-level routing confidence, improving performance with minimal computational overhead.