arXiv stat.ML
· Papers
Sequential Correlations Change In-Context Learning: Effective Context Length and Architectural Mismatch
arXiv:2607.03660v1 Announce Type: new Abstract: Modern sequence models have a striking capacity for in-context learning (ICL); they can perform new tasks based only on examples given in the prompt. Understanding how this ability emerges requires theory that captures important properties of natural data. Linear regressi