arXiv Machine Learning
Jun 19
Critical Percolation as a Synthetic Data Model for Interpretability
arXiv:2606. 20347v1 Announce Type: new Abstract: Neural networks learn features that reflect the hierarchical, multi-scale structure of natural data.
Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
arXiv:2507. 14159v2 Announce Type: replace-cross Abstract: Predicting critical phenomena from limited labeled data remains a challenging task in statistical physics.
Related stories
arXiv Machine Learning
Jun 17
Dropout Neural Network Training Viewed from a Percolation Perspective
arXiv:2512. 13853v2 Announce Type: replace Abstract: In this work, we investigate the existence and effect of percolation in training deep Neural Networks (NNs) with dropout.
arXiv Machine Learning
Aug 4
Tunneling the Loss Landscape: Bypassing Memorization with Monte Carlo Parameter Swapping
arXiv:2608. 01833v1 Announce Type: cross Abstract: Grokking is a striking phenomenon in neural network training, where a model can undergo a prolonged period of pure memorization before abrupt generalization.
arXiv Machine Learning
Aug 10
Cascading Through the Hierarchy: Regularizer-Induced Feature Detection as Phase Transitions in Deep Linear Neural Networks
arXiv:2608. 06597v1 Announce Type: cross Abstract: A scientific theory of deep learning, comprising learning dynamics and statistical properties of learned models, is rapidly gaining attention.
arXiv Machine Learning
Jul 1
Revisiting the Volume Hypothesis
arXiv:2606. 31282v1 Announce Type: new Abstract: Modern deep neural networks often contain far more parameters than needed to fit their training data, yet they achieve impressive generalization.
arXiv AI
Jul 29
Dual-Level Atomic and Coordination Geometry Learning for Crystal Property Prediction Using Graph Neural Networks
arXiv:2607. 24818v1 Announce Type: cross Abstract: Accurate prediction of crystal properties remains a key challenge in computational materials science.
arXiv Machine Learning
1d ago
Generative Learning of Separatrices
arXiv:2608. 14743v1 Announce Type: new Abstract: The identification and reconstruction of the boundaries separating basins of attraction in multistable, multidimensional dynamical systems presents a fundamental challenge in computational dynamics.
arXiv Machine Learning
Jun 2
Latent Diffusion Pretraining for Crystal Property Prediction
arXiv:2606. 00776v1 Announce Type: new Abstract: Fast and accurate prediction of crystal properties is a central challenge in new materials design.
arXiv Machine Learning
Jul 7
Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs
arXiv:2512. 18454v3 Announce Type: replace Abstract: Predictive machine learning models generally excel on in-distribution data, but their performance degrades on out-of-distribution (OOD) inputs.
arXiv Machine Learning
1d ago
Differentiable Thermodynamic Phase-Equilibria for Machine Learning
arXiv:2603. 11249v4 Announce Type: replace Abstract: Accurate prediction of phase equilibria remains a central challenge in chemical engineering.
arXiv Machine Learning
Jul 9
Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories
arXiv:2607. 07127v1 Announce Type: cross Abstract: Lattice field theory is the workhorse of non-perturbative physics, used to simulate phenomena from the strong nuclear force to critical phenomena in materials.
arXiv AI
Jun 9
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science
arXiv:2606. 07712v1 Announce Type: cross Abstract: Progress in AI-driven crystal materials science has so far been carried by narrow architectures purpose-built for individual tasks -- graph neural networks for property prediction, diffusion and flow-matching models for crystal generation -- each excelling within its niche yet unable to act as a shared backbone across the full spectrum of materials problems.