研究人员开发了新的方法来分析计算机视觉中混合专家（MoE）模型的内部工作机制。他们的工作超越了简单地检查数据如何被路由到模型内的特定“专家”，而是专注于每个专家实际编码的内容。研究发现，动/静物区分是专家划分的主要因素，并且这种专业化在不同的模型初始化中是稳定的。 AI
影响 提供了对视觉MoE模型内部表征的更深入见解，可能导致更具可解释性和鲁棒性的AI系统。
排序理由 该集群包含一篇详细介绍分析AI模型新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.20610v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convolutional MoE m…
Mixture-of-Experts (MoE) models are often interpreted by analysing which categories are routed to which experts. However, routing alone does not reveal what each expert actually encodes. We train sparsely-gated convolutional MoE models with a contrastive objective on natural imag…