QuBD extends algorithmic complexity estimation to quantized DNN weights, revealing that complexity decreases during learning, increases with overfitting, follows grokking patterns, and correlates with generalization.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
Feature-space sampling in GCNNs preserves 3D classification accuracy with coarse discretization, enabling precomputation and faster training of equivariant models.
Muon optimizer improves performance over Adam in equivariant networks on ModelNet40 and produces solutions with larger Hessian curvature, more regular loss surfaces, and higher stable/effective ranks.
Explicit E(3)-equivariance in neural CFD surrogates improves generalization on diverse-geometry hemodynamics benchmarks but degrades in-distribution performance on strongly aligned aerodynamics data, consistently beating data augmentation.
Stronger physics priors in neural networks for spatio-temporal shear flow forecasting yield substantially lower training carbon footprints than weak or no priors, though inference savings are less consistent.
mlip v2 is a new software release that integrates API redesign, e3j backend, eSEN model, improved charge modeling, and expanded simulation capabilities to support larger-scale molecular modeling.