arXiv:2607.04333v1 Announce Type: new Abstract: Grokking -- generalization arriving long after training-set interpolation -- can be accelerated by structure-agnostic interventions: gradient filtering, weight-norm clamping, geometric penalties on hidden representations. Whether the delay specifically measures the time to form task-structured representations has remained an observational claim. We test it causally by injecting representational priors of varying structural content into a one-layer transformer learning modular addition: a supervised-contrastive auxiliary loss whose positives encod
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG