A Distributional Simplicity Bias in the Learning Dynamics of TransformersRiccardo Rende,Federica Gerace,Alessandro Laio,Sebastian GoldtNeurIPS 2024(2024)引用 0|浏览0暂无评分关键词Transformers,Natural Language Processing,Sequential Learning,Simplicity BiasAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要