Learned Structure Shows Up Earlier in the Task's Own Basis: A Controlled Look at a Synchronisation Precursor in Grokking

arXiv:2606.12966 · cs.LG, cs.NE · Submitted 2026-06-11 · Read on arXiv

cs.LG, cs.NE

Submitted: 2026-06-11

Updated: 2026-10-11

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Frequency Synchronization Degree — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks