Hugging Face Trending Papers June 11, 2026

Circuit Synchronization Precedes Generalization: Causal Evidence from Fourier Structure in Grokking Transformers

Read the original on Hugging Face Trending Papers →

Grokking -- where a transformer on modular arithmetic suddenly transitions from near-chance to near-perfect validation accuracy -- is attributed to a Fourier circuit, but its timing, causal structure, and controllability remain poorly understood. We introduce the Frequency Synchronization Degree (FSD), a normalised, permutation-tested metric for Fourier circuit synchronisation requiring no prior circuit knowledge.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

llms

arXiv Machine Learning

Jun 18

Attention as Frustrated Synchronization

arXiv:2606. 18694v1 Announce Type: new Abstract: A network of oscillators that synchronizes perfectly computes nothing further, so an attention architecture built from synchronization must locate its computation in structured departures from agreement.

By Joshua Nunley

llms

arXiv AI

Jul 7

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

arXiv:2607. 05104v1 Announce Type: cross Abstract: Grokking -- the delayed onset of generalization long after a network has fit its training set - -is usually studied in models too large to read completely and reported from single training runs.

By Yoshiyuki Ootani

llms

arXiv AI

Jul 9

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics

arXiv:2607. 06639v1 Announce Type: cross Abstract: On modular arithmetic, a network's embedding keeps compressing for tens of thousands of steps after it has already generalized.

By Truong Xuan Khanh

llms rag benchmarks safety

arXiv Machine Learning

Jul 7

Structure-Specific Representational Priors Causally Control the Grokking Delay

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.

By Gunner Levi Howe

llms

arXiv Machine Learning

Jul 15

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

arXiv:2607. 12735v1 Announce Type: new Abstract: Companion work showed the grokking delay is causally the time to form task-structured representations, injectable via a contrastive prior.

By Gunner Levi Howe

safety

arXiv AI

Jul 22

Circuit Claims Depend on What Is Extracted and How It Is Compared

arXiv:2607. 18921v1 Announce Type: cross Abstract: Circuit extraction identifies a small set of model components whose presence preserves a target behavior under ablation, and the resulting circuit is often read as the mechanism behind that behavior.

By Yang Sheng, Jie Fu

llms reinforcement-learning efficiency benchmarks

Related stories

Attention as Frustrated Synchronization

Grokking Is Conditional and Fragile: A Fully-Tractable, Multi-Seed Study at 12K Parameters

At-Grok Is Not Converged:A Measurement-Validity Audit for Grokking Representation Metrics

Structure-Specific Representational Priors Causally Control the Grokking Delay

What Makes a Representational Prior Work? Feature Families, Label-Free Invariances, and Critical Windows in Grokking

Circuit Claims Depend on What Is Extracted and How It Is Compared