IEEE

A High-Performance Knowledge Distillation Framework Based on Temperature Decoupling

Abstract: Knowledge Distillation (KD) has become a widely used model compression technique in large language models (LLMs). Most mainstream KD methods adopt a temperature-sharing mechanism, where both ...
IEEE

Knowledge Distillation-Based Anomaly Detection via Adaptive Discrepancy Optimization

Abstract: Knowledge distillation has emerged as a primary solution for anomaly detection, leveraging feature discrepancies between teacher–student (T–S) networks to locate anomalies. However, previous ...