arXiv:2608. 20295v1 Announce Type: new Abstract: Sparse pursuit after dictionary learning can yield a precise atom support even when its physical interpretation is not justified by the calibration data, especially for highly coherent dictionaries where alternative calibration-compatible dictionaries may assign different physical meanings to the same selected support.
arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.
arXiv:2606. 04100v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) enable efficient and accurate atomistic simulations but depend critically on the quality and diversity of the training data.
arXiv:2509. 10033v2 Announce Type: replace Abstract: Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms.
The paper introduces truncated automatic sparse differentiation (ASD) to efficiently compute higher‑order derivatives, such as Hessians, for machine learning interatomic potentials (MLIPs). By exploiting the locality of atomic interactions, ASD identifies a sparsity pattern that allows exact Hessian calculation for large porous materials, while truncated ASD discards distant, small Hessian entries to achieve order‑of‑magnitude speedups with minimal loss in predictive accuracy. The authors demonstrate these methods on several foundational MLIPs, showing modest speedups for full ASD and significant gains for the truncated approach.
arXiv:2608. 13882v1 Announce Type: new Abstract: Claims about the benefit of depth depend on the complexity assigned to a representation.
arXiv:2609.36451v1 Announce Type: new Abstract: Large language models often preserve meaning despite substantial changes in wording, style, and syntax, while small semantic edits can systematically a...
arXiv:2602. 16568v2 Announce Type: replace-cross Abstract: Sparse recovery is among the most well-studied problems in learning theory and high-dimensional statistics.
arXiv:2609.39090v1 Announce Type: cross Abstract: Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of...
AtomWorld-Mem is a memory‑restored atomistic world model that reconstructs hidden world states from incomplete crystal snapshots, enabling more accurate long‑horizon atomistic evolution. It uses spatial encoders to capture multi‑scale keyframes and integrates short‑term event memory with long‑term structural memory to predict future states. The restored state guides vacancy‑mediated events in kinetic Monte Carlo simulations, improving progress under fixed event budgets while preserving fidelity across energetic, structural, and transport observables, and it transfers zero‑shot across unseen alloy‑temperature scenarios.
arXiv:2606. 00401v1 Announce Type: cross Abstract: Simulating large molecular systems comprising thousands of atoms requires highly scalable methodologies.
The paper presents NuCLR, a multi-task neural network that learns nuclear data representations to predict charge radii and electric‑quadrupole transition strengths across hundreds of nuclides. Using held‑out ensembles, the model achieves a charge‑radius RMS deviation of 0.0147 fm and a B(E2) RMS deviation of 0.192 e²b², comparable to leading nuclear models. The authors provide error bars indicating where additional experimental data could improve predictions, positioning NuCLR as a data‑driven surveyor of nuclear structure.