icl-gd-gap-constant-across-scale

OUT premise — summaries/2026/08/24/shen-2023-icl-not-gd-s1-icl-demonstrations.md

Created 2026-08-25T02:58:31+00:00

The ICL–GD gap remains roughly constant across model sizes from 1.5B to 7B parameters, suggesting the phenomenon is architectural rather than a scaling artifact.