This paper applies extreme learning machines to model aerodynamic self-excited forces in long-span bridge-deck cross-sections, supporting the prediction of aerodynamic instabilities and bridge safety. The approach uses forced-oscillation data from CFD or wind-tunnel experiments.
See LICENSE fileaeroelasticitylong-span bridgesextreme learning machines
The paper investigates nonlinear excitation of optical anapoles at the nanoscale and designs a localized electromagnetic excitation without far-field radiation using an exact current multipole expansion and the exact anapole condition.
See LICENSE fileOptical anapolesNonlinear opticsNanoelectromagnetics
Targets electromagnetic radiation and wave-field modeling by combining physics embedding with an evolving kernel in scalable physics-informed neural networks, with attention to oscillatory behaviors, singular excitations, and absorbing boundaries.
See LICENSE filePhysics-Informed Neural NetworksElectromagnetic Wave ModelingPhysics Embedding
PHASE uses reusable solution operators and residual error correction to model multiscale incompressible magnetohydrodynamics across varying parameter settings, supporting fast inference for plasma dynamics.
See LICENSE filemagnetohydrodynamicssurrogate modelingmulti-regime modeling
A physics-guided machine unlearning method for cyber-physical systems uses physical residuals as safety constraints, steering model weight updates toward physically feasible regions while removing poisoned behavioral influence.
See LICENSE fileMachine UnlearningPhysics-Guided LearningCyber-Physical Systems
PneuTac targets tactile manipulation in soft pneumatic robotics by unifying robot motion and vision-based tactile perception within an MPM-Gaussian splatting simulation. The approach addresses calibration gaps that limit efficient simulation of compliant robotic contact.
See LICENSE filesoft pneumatic robotstactile manipulationcontact simulation
This bioacoustics paper introduces a sampling-frequency-independent frontend that processes recordings at their native rates, combined with a Fourier Neural Operator backbone for heterogeneous multi-taxa classification while reducing high-frequency information loss from resampling.
See LICENSE filebioacousticsheterogeneous sampling ratesFourier Neural Operator
This paper applies physics-informed neural networks to reconstruct molten pool flow fields from high-speed video for wire-arc directed energy deposition, where extreme temperatures and intense arc illumination make direct flow sensing difficult.
See LICENSE fileMolten Pool FlowHigh-Speed Video ReconstructionPhysics-Informed Neural Networks
The paper presents a reduced Cartesian framework for planar, axially compressible tendon-driven continuum robots, propagating equilibrium configurations along prescribed tendon-force and tendon-displacement trajectories. A Taylor–Galerkin reduction condenses the backbone representation into two global position fields while retaining full-shape propagation.
See LICENSE filecontinuum roboticstendon-driven robotsreduced kinetostatics
This paper develops reduced-order modeling for mechanical metamaterials, addressing buckling and pattern transformation while accounting for local, nonlocal, and patterning fluctuation effects.
See LICENSE filemechanical metamaterialsreduced-order modelingcomputational homogenization
Introduces the Tau-orthogonal framework for lattice Boltzmann turbulence simulations, using macroscopic-velocity forcing to model subgrid-scale effects in large eddy simulations.
See LICENSE fileTurbulence simulationLattice Boltzmann methodSubgrid-scale model
This paper studies how external body knowledge, successful experience, and executable skills improve GPT-6-Astra control of an XLeRobot in simulated and physical elevator-button tasks, focusing on robot manipulation and Sim2Real transfer.
See LICENSE fileRobot ManipulationSim2Real TransferEmbodied Intelligence
SCOPE addresses full-field recovery from sparse observations in PDE systems by coupling full-field latent prediction with physical reconstruction. The method targets incomplete physical fields where measurements do not uniquely determine the underlying state.
See LICENSE filePDE inferenceSparse observationsPhysical field reconstruction
This paper presents a simulator-refined diffusion approach for inverse design of radio-frequency PCB layouts, targeting quantitative electromagnetic specifications through S-parameter-conditioned generation and examining the role of gradient-based guidance during sampling.
See LICENSE fileRF PCBInverse DesignDiffusion Models
SINO is a scale-invariant neural operator for partial differential equation solving, using low-rank parameterization to represent unresolved physics and closure mechanisms in coarse-grid computations.
See LICENSE filescale-invariant neural operatorpartial differential equationsphysics closure
SPOpInf is a non-intrusive method that learns stochastic differential equations from data for quadratically nonlinear systems with additive noise, supporting reduced-order modeling of complex stochastic dynamics and turbulent flows.
See LICENSE filestochastic operator inferencestochastic differential equationreduced-order modeling
TaiJi introduces a spatiotemporal adaptive ensemble framework that fuses data-driven machine-learning weather models with physics-based numerical weather prediction forecasts using state-conditional weighting across variables, pressure levels, lead times, and regions.
See LICENSE fileweather forecastingmachine learningnumerical weather prediction
The paper generalizes fixed-lattice cluster expansions and atomic cluster expansions by representing both rotation and permutation symmetries, supporting equivariant representations for atomistic materials modeling.
See LICENSE filecluster expansionatomic interactionsrotation equivariance
This paper investigates applying physics-informed neural networks to Einstein’s equations of General Relativity, exploring continuous representations of spacetime solutions without a predefined computational mesh.
See LICENSE filePhysics-Informed Neural NetworksGeneral RelativityEinstein Equations