arxiv
PublishedMay 12, 2026 at 4:00 AM
Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
Publisher summary· verbatim
arXiv:2605.09724v1 Announce Type: new Abstract: Existing accounts of grokking explain the phenomena in terms of mechanistic frameworks such as circuit efficiency or lazy-to-rich transitions. However, despite a known dependence between grokking and model size, how model capacity shapes grokking remai
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivThe Steering Budget: Examples beat Knobs17harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs17harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination17harxivWhen a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models17hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗