Effective cascade dimension D(t) crosses D=1 at the grokking transition in MLPs and Transformers, with opposite directions for modular addition versus XOR, consistent with attraction to a shared critical manifold.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Aging in depinning models generates global oscillatory stick-slip regimes, with king avalanches in mean field and alternating avalanche activity intervals in 2D without system-size events.
citing papers explorer
-
Dimensional Criticality at Grokking Across MLPs and Transformers
Effective cascade dimension D(t) crosses D=1 at the grokking transition in MLPs and Transformers, with opposite directions for modular addition versus XOR, consistent with attraction to a shared critical manifold.
-
Global Oscillations in Depinning Models with Aging
Aging in depinning models generates global oscillatory stick-slip regimes, with king avalanches in mean field and alternating avalanche activity intervals in 2D without system-size events.