arxiv
PublishedMay 18, 2026 at 4:00 AM
Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
Publisher summary· verbatim
arXiv:2605.15787v1 Announce Type: cross Abstract: Why does a Transformer that has memorized its training set wait thousands of steps before it generalizes? Existing accounts locate this delay in norm minimization, feature emergence, or the late discovery of sparse subnetworks. These explanations cap
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
arxivIMEX Interaction-Based Model Explanation6harxivDialogueVPR: Towards Conversational Visual Place Recognition6harxivHuman AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach6harxivOrchestrating Power Grid Studies with Multi-Agent AI and MCP Servers6hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗