Generalization vs. Memorization in Autoregressive Deep Learning: Or, Examining Temporal Decay of Gradient CoherenceFoundation models trained as autoregressive PDE surrogates hold significant promise for accelerating scientific discovery through their capacity to both extrapolate beyond training regimes and…James Amarel, Nicolas Hengartner, Robyn Miller et al.·Aug 18, 2025SaveLearn
Time Reversible Integration of the Landau-Lifshitz-Gilbert EquationA method for time-reversible numerical integration of the deterministic Landau-Lifshitz Gilbert equation by means of a second order Suzuki-Trotter decomposition is presented and tested against…Moritz Sallermann, Thorsteinn Freygardsson, Sergei Egorov et al.·Aug 18, 2025SaveLearn
Rapid Variable Resolution Particle Initialization for Complex GeometriesThe accuracy of meshless methods like Smoothed Particle Hydrodynamics (SPH) is highly dependent on the quality of the particle distribution. Existing particle initialization techniques often struggle…Navaneet Villodi, Prabhu Ramachandran·Aug 18, 2025SaveLearn
Hyperparameter Optimization in the Estimation of PDE and Delay-PDE models from dataWe propose an improved method for estimating partial differential equations and delay partial differential equations from data, using Bayesian optimization and the Bayesian information criterion to…Oliver Mai, Tim W. Kroll, Uwe Thiele et al.·Aug 18, 2025SaveLearn
AFSI: Automated Fluid-Structure Interaction Solver Development for Nonlinear Solid MechanicsAFSI is a novel, open-source fluid-structure interaction (FSI) solver that extends the capabilities of the FEniCS finite element library through an immersed boundary (IB) framework. Designed to…Pengfei Ma, Li Cai, Xuan Wang et al.·Aug 16, 2025SaveLearn
DPI-SPR: A Differentiable Physical Inversion for Shadow Profile Reconstruction Framework in Forward Scatter RadarForward scatter radar (FSR) has emerged as an effective imaging modality for target detection, utilizing forward scattering (FS) signals to reconstruct two-dimensional shadow profile images of…ShuQi Lei, Gan Yu, Yuan Tian et al.·Aug 15, 2025SaveLearn
An efficient and robust high-order compact ALE gas-kinetic scheme for unstructured meshesFor the arbitrary-Lagrangian-Eulerian (ALE) calculations, the geometric information needs to be calculated at each time step due to the movement of mesh. To achieve the high-order spatial accuracy, a…Yibo Wang, Xing Ji, Liang Pan·Aug 15, 2025SaveLearn
Novel discretization method to calculate g-functions of vertical geothermal boreholes with improved accuracy and efficiencyThe calculation of g-functions is essential for the design and simulation of geothermal boreholes. However, existing methods, such as the stacked finite line source (SFLS) model, face challenges…Yue Yang, Xiaodong Yang, Chenhui Lin et al.·Aug 15, 2025SaveLearn
Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT ModulesMonitoring the degradation state of Insulated Gate Bipolar Transistor (IGBT) modules is essential for ensuring the reliability and longevity of power electronic systems, especially in safety-critical…Andrea Urgolo, Monika Stipsitz, Hèlios Sanchis-Alepuz·Aug 14, 2025SaveLearn
Sum-of-Gaussians tensor neural networks for high-dimensional Schr\"odinger equationWe propose an accurate, efficient, and low-memory sum-of-Gaussians tensor neural network (SOG-TNN) algorithm for solving the high-dimensional Schr\"odinger equation. The SOG-TNN utilizes a low-rank…Qi Zhou, Teng Wu, Jianghao Liu et al.·Aug 14, 2025SaveLearn
MCP-Enabled LLM for Meta-optics Inverse Design: Leveraging Differentiable Solver without LLM ExpertiseAutomatic differentiation (AD) enables powerful metasurface inverse design but requires extensive theoretical and programming expertise. We present a Model Context Protocol (MCP) assisted framework…Yi Huang, Bowen Zheng, Yunxi Dong et al.·Aug 14, 2025SaveLearn
A Pseudo-Fermion Propagator Approach to the Fermion Sign ProblemIn this work, within the framework of path integral Monte Carlo, we construct a pseudo-fermion propagator by replacing the original fermionic determinant with its absolute value. This modified…Yunuo Xiong, Hongwei Xiong·Aug 13, 2025SaveLearn
Reproducing and Extending Brownian Motion in Optical Trap: A Computational Reimplementation of Volpe and Volpe (2013)We present a re-representation and independent simulation of the model introduced by Giorgio Volpe and Giovanni Volpe in their 2013 study of a Brownian particle in an optical trap (Volpe and Volpe,…Eyad I. B Hamid·Aug 11, 2025SaveLearn
Adaptive Online Emulation for Accelerating Complex Physical SimulationsComplex physical simulations often require trade-offs between model fidelity and computational feasibility. We introduce Adaptive Online Emulation (AOE), which dynamically learns neural network…Tara P. A. Tahseen, Nikolaos Nikolaou, Luís F. Simões et al.·Aug 11, 2025SaveLearn
A hybrid electromechanical phase-field and deep learning framework for predicting fracture in dielectric nanocompositesThe accurate and efficient prediction of crack propagation in dielectric materials is a critical challenge in structural health monitoring and the design of smart systems. This work presents a hybrid…Aamir Dean, Jaykumar Mavani, Betim Bahtiri et al.·Aug 10, 2025SaveLearn
How to simulate L\'evy flights in a steep potential: An explicit splitting numerical schemeWe propose an effective explicit numerical scheme for simulating solutions of stochastic differential equations with confining superlinear drift terms, driven by multiplicative heavy-tailed L\'evy…Ilya Pavlyukevich, Olga Aryasova, Alexei Chechkin et al.·Aug 10, 2025SaveLearn
Benchmarking Self-Driving LabsA key goal of modern materials science is accelerating the pace of materials discovery. Self-driving labs, or systems that select experiments using machine learning and then execute them using…Adedire D. Adesiji, Jiashuo Wang, Cheng-Shu Kuo et al.·Aug 8, 2025SaveLearn
TorchSim: An efficient atomistic simulation engine in PyTorchWe introduce TorchSim, an open-source atomistic simulation engine tailored for the Machine Learned Interatomic Potential (MLIP) era. By rewriting core atomistic simulation primitives in PyTorch,…Orion Cohen, Janosh Riebesell, Rhys Goodall et al.·Aug 8, 2025SaveLearn
Real-time physics-informed reconstruction of transient fields using sensor guidance and higher-order time differentiationThis study proposes FTI-PBSM (Fixed-Time-Increment Physics-informed neural network-Based Surrogate Model), a novel physics-informed surrogate modeling framework designed for real-time reconstruction…Hong-Kyun Noh, Jeong-Hoon Park, Minseok Choi et al.·Aug 8, 2025SaveLearn
Advancing Material Modeling in Hydrocodes Beyond Equations of StateWe present a multiscale simulation framework that couples the Finite Element Method with molecular dynamics. Bypassing traditional equations of state (EOS) by using in-line atomistic simulations, the…Tim A. Linke, Dane M. Sterbentz, Jean-Pierre R. Delplanque et al.·Aug 8, 2025SaveLearn
FDTRImageEnhancer: Combining Physics-Informed Deconvolution and Microstructure-Aware Deep Learning to Enhance Thermal ImagesWe present FDTRImageEnhancer, an open-source computational framework that improves thermal conductivity mapping from Frequency Domain ThermoReflectance (FDTR) phase data by integrating a…Alesanmi Richmond Rerelope Odufisan·Aug 8, 2025SaveLearn
Hybrid Physics-Machine Learning Models for Quantitative Electron Diffraction RefinementsHigh-fidelity electron microscopy simulations required for quantitative crystal structure refinements face a fundamental challenge: while physical interactions are well-described theoretically,…Shreshth A. Malik, Tiarnan A. S. Doherty, Benjamin Colmey et al.·Aug 8, 2025SaveLearn
Identifying Optimal Regression Models For DEM Simulation DatasetsDeveloping fast regression models (surrogate/metamodels) from DEM data is key for practical industrial application to allow real-time evaluations. However, benchmarking different models is often…B. D. Jenkins, A. L. Nicusan, A. Neveu et al.·Aug 7, 2025SaveLearn
Hyperbolic tiling neighborhoods in O(1) timeTilings of the hyperbolic plane are of significant interest among many branches of mathematics, physics and computer science. Yet, their construction remains a non-trivial task. Current approaches…Yanick Thurn, Manuel Schrauth, Johanna Erdmenger·Aug 6, 2025SaveLearn
Physics-Informed Neural Network for Elastic Wave-Mode SeparationMode conversion in non-homogeneous elastic media makes it challenging to interpret physical properties accurately. Decomposing these modes correctly is crucial across various scientific areas. Recent…E. A. B. Alves, P. D. S. de Lima, D. H. G. Duarte et al.·Aug 6, 2025SaveLearn