The paper presents a differentiable 3D Gaussian Splatting-SPH coupling model for solid mechanics, supporting forward simulation of mechanical responses and inverse analysis.
See LICENSE filesolid mechanicsdifferentiable simulation3D Gaussian Splatting
The paper develops an electromagnetic inversion scheme that combines stochastic optimization with plug-and-play regularization for contrast-source inversion. In multi-transmitter configurations, it selects one random contrast source per iteration instead of solving for all transmitters, reducing the per-iteration computational burden.
See LICENSE fileelectromagnetic inversioncontrast-source inversionstochastic optimization
The paper presents a locally conservative enriched linearized neural network method for the Darcy flow model, using piecewise constant functions on an auxiliary domain subdivision to enforce local mass conservation.
See LICENSE fileDarcy flowlocal mass conservationelliptic PDEs
BAT-NO is a structural-mechanics surrogate for autoregressively predicting transient vehicle-component responses and crashworthiness under varying boundary conditions.
See LICENSE filevehicle crashworthinessneural operatorfinite element surrogate
Predicts advection-dominated microplastic transport in saturated soils efficiently using only geometric information, supporting computational analysis of particle migration through complex porous media.
See LICENSE filemicroplastic transportsaturated soilporous media
An SE(3)-equivariant denoising diffusion model learns the configurational distribution of amorphous oxides and generates diverse structural ensembles beyond conventional DFT and machine-learned-potential simulations.
See LICENSE fileamorphous oxidesequivariant diffusion modelmaterials generation
This study investigates non-modal perturbations excited by free-stream forcing in hypersonic blunt-nose boundary layers, focusing on the effects of wall temperature and nose bluntness.
See LICENSE fileHypersonic Boundary LayersNon-Modal PerturbationsShock Fitting
HFS-TransNet addresses computationally challenging quasi-static Biot fluid-solid interactions in poroelastic media by combining a data-driven TransNet module with a fixed-stress transfer scheme.
See LICENSE filePoroelasticityBiot systemFluid-solid interaction
A data-driven method jointly infers Hamiltonian functions and underlying Poisson tensors from vector-field samples, enabling structured dynamical-system modeling without assuming the Hamiltonian or Poisson structure is known.
See LICENSE fileHamiltonian dynamicsLie-Poisson structuresvector-field inference
A dual-stage cascade reservoir computing framework jointly forecasts the timing and peak intensity of rare, large-amplitude extreme events in dynamical systems.
See LICENSE filereservoir computingextreme event forecastingcascade learning
The paper presents a label-free PINN for the reliability of spatially variable slopes, combining finite-element virtual-work losses with incremental strength reduction for non-associated Mohr-Coulomb plasticity.
See LICENSE fileslope reliabilityphysics-informed neural networkneural operator
A latent Lagrangian framework reduces the order of forced nonlinear dynamical systems by learning latent coordinates and neural representations of kinetic and potential energies, while force supervision removes the need for an ODE solver during training.
See LICENSE filenonlinear dynamical systemsreduced-order modelingphysics-informed machine learning
This paper proposes a data-driven framework for estimating the Bayesian Cramér-Rao bound in high-dimensional imaging inverse problems with complex, analytically intractable priors. It reformulates the inverse problem in the latent space of a pre-trained model to address prior-score modeling and high-dimensional Bayesian Fisher information matrix computation.
See LICENSE fileBayesian Cramér-Rao BoundHigh-Dimensional ImagingImaging Inverse Problems
This paper develops phase-field fracture modeling for fiber-reinforced shells using a replaceable constitutive operator and a geometrically exact shell formulation. The formulation uses Green-Lagrange strain with the Cholesky factor of the reference metric to represent the composite shell mechanics.
See LICENSE filephase-field fracturecomposite shellsconstitutive modeling
The paper investigates involution-preserving properties of semi-discrete Active Flux methods on unstructured triangular meshes, using two-dimensional linear acoustics and Maxwell equations as model problems.
See LICENSE fileActive Flux methodinvolution preservationunstructured triangular meshes
REACT addresses physically and chemically consistent reconstruction of sea surface pH from sparse observations, supporting ocean acidification monitoring and marine carbon-cycle research in the ocean geophysical domain.
See LICENSE fileOcean acidificationSea surface pHMarine active tracers
This materials-science paper applies reinforcement learning to the discrete composition channel of a crystal generator for property-targeted inverse design, while examining validated gains and reward hacking.
See LICENSE fileinverse materials designcrystal generationreinforcement learning
This paper studies oscillation death in two-dimensional incompressible flow interactions between a cylinder and a NACA0012 airfoil, combining direct numerical simulation with a synchronization-theoretic autoencoder.
See LICENSE fileoscillation deathcylinder-airfoil interactionsynchronization theory
ADSD is a diagnosis-first framework for improving scientific-computing numerical solvers by connecting execution feedback to reusable solver-improvement skills.
See LICENSE fileNumerical SolversAuto-DiagnosisSkill Discovery