AI RESEARCH

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

arXiv CS.LG

ArXi:2505.14808v2 Announce Type: replace-cross The transformer's remarkable ability to perform in-context learning (ICL) has sparked a wide range of studies designed to understand its strengths and limitations. However, a theoretical understanding of when ICL can and cannot generalize beyond its pre-