A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.
Title resolution pending
11 Pith papers cite this work, alongside 14,424 external citations. Polarity classification is still indexing.
11
Pith papers citing it
14.4k
external citations · Crossref
fields
cs.NE 3 astro-ph.SR 1 cond-mat.dis-nn 1 cond-mat.soft 1 cs.CL 1 cs.ET 1 cs.LG 1 physics.plasm-ph 1 q-bio.PE 1years
2026 11verdicts
UNVERDICTED 11representative citing papers
A single energy-based model trained on LAPD plasma data enables diagnostic reconstruction, inverse inference of probe position, conditional trend sampling, and unconditional mode reproduction for potential anomaly detection.
Geometric entropy on the N-sphere sets retrieval phase boundaries in continuous thermal dense associative memories, achieving maximum capacity α=0.5 at zero temperature with kernel-dependent critical lines separating retrieval from failure.
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
Casimir-stabilized protocell clusters form ε-machines whose attractor states and transitions create emergent prebiotic information through physical memory rather than molecular polymers.
Hybrid neural network predicts eruptive versus confined solar flares from SDO/HMI magnetogram sequences, reports good performance, and links results to magnetic flux cancellation in polarity inversion lines.
Physical neural computing platforms using diverse materials offer complementary strengths for efficient on-device AI, with no single substrate excelling in all dimensions.
LLM hallucinations arise from task-dependent basins in latent space, with separability varying by task and geometry-aware steering reducing their probability.
KLR Hopfield networks store up to 16-20 times their neuron count before dynamical instability from crosstalk noise causes collapse, with sharp attractor boundaries observed via morphing and SNR analysis.
Cell-to-cell variability selects for aligned, motif-enriched gene regulatory networks that are robust to developmental noise and mutations.
Spintronic CiM shows uniform temperature that increases linearly with participating memory cells and decreases linearly with array size.
citing papers explorer
-
Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
A Random Matrix Theory method identifies growing Correlation Traps in neural network weight spectra during an 'anti-grokking' overfitting phase, and applies the same diagnostic to some foundation LLMs.
-
Energy-based models for diagnostic reconstruction and analysis in a laboratory plasma device
A single energy-based model trained on LAPD plasma data enables diagnostic reconstruction, inverse inference of probe position, conditional trend sampling, and unconditional mode reproduction for potential anomaly detection.
-
Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory
Geometric entropy on the N-sphere sets retrieval phase boundaries in continuous thermal dense associative memories, achieving maximum capacity α=0.5 at zero temperature with kernel-dependent critical lines separating retrieval from failure.
-
Efficient event-driven retrieval in high-capacity kernel Hopfield networks
Asynchronous sequential updates in KLR Hopfield networks produce statistically indistinguishable trajectories from synchronous dynamics, achieve empirical capacities near P/N=30, and converge with event counts close to initial Hamming distance.
-
Emergent Information Formation in Prebiotic Protocell Clusters: A Computational Mechanics Framework of $\epsilon$-Machines and Attractor Memory
Casimir-stabilized protocell clusters form ε-machines whose attractor states and transitions create emergent prebiotic information through physical memory rather than molecular polymers.
-
Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network
Hybrid neural network predicts eruptive versus confined solar flares from SDO/HMI magnetogram sequences, reports good performance, and links results to magnetic flux cancellation in polarity inversion lines.
-
Beyond Silicon: Materials, Mechanisms, and Methods for Physical Neural Computing
Physical neural computing platforms using diverse materials offer complementary strengths for efficient on-device AI, with no single substrate excelling in all dimensions.
-
Hallucination Basins: A Dynamic Framework for Understanding and Controlling LLM Hallucinations
LLM hallucinations arise from task-dependent basins in latent space, with separability varying by task and geometry-aware steering reducing their probability.
-
Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks
KLR Hopfield networks store up to 16-20 times their neuron count before dynamical instability from crosstalk noise causes collapse, with sharp attractor boundaries observed via morphing and SNR analysis.
-
How is gene-regulatory evolution affected by cell-to-cell variability?
Cell-to-cell variability selects for aligned, motif-enriched gene regulatory networks that are robust to developmental noise and mutations.
-
Computing In Spintronic Memory: A Thermal Perspective
Spintronic CiM shows uniform temperature that increases linearly with participating memory cells and decreases linearly with array size.