1
The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level
ICML 2026 顶会论文：深入 Mixture-of-Experts 语言模型的专家级别内部机制，揭示专家如何协同与对抗。
arXiv:2604.02178v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Lan…