This high-energy physics work embeds a Physics-Informed Neural Network in the conformal z-plane to construct the pion electromagnetic form factor Fπ(s) directly from first principles across spacelike and timelike domains, enforcing physical normalization, symmetry, analyticity, and dispersion constraints.
See LICENSE filePhysics-Informed Neural Networkpion electromagnetic form factormuon anomalous magnetic moment
PTNO trains a neural operator directly on noisy, low-cost Monte Carlo labels for particle transport in radiative transfer and plasma physics, reducing reliance on expensive converged simulations.
See LICENSE fileneural operatorparticle transportMonte Carlo simulation
ROBIN-PIP targets robust Bayesian field-level inference for galaxy surveys at nonlinear scales, combining physics-informed priors with more expressive representations of the galaxy bias relation.
See LICENSE fileBayesian field-level inferencephysics-informed priorsgalaxy bias
ScaleSplit-NO is a neural-operator method for three-dimensional turbulence prediction that exploits turbulence scale structure, reducing memory requirements and reliance on costly full-resolution training data in high-resolution simulation workflows.
See LICENSE fileNeural Operator3D TurbulenceTurbulence Prediction
The paper presents a structure-preserving Fourier Neural Operator for long-time Cahn-Hilliard phase-field dynamics using coarse temporal supervision, targeting efficient surrogate prediction during computationally intensive late-stage coarsening while addressing error accumulation in repeated time stepping.
See LICENSE fileCahn-Hilliard dynamicsFourier neural operatorphase-field simulation
A quantum-classical algorithm for electrical power distribution network reconfiguration combines a radiality-preserving branch-exchange encoding with iterative warm-start quantum imaginary-time evolution to minimize active line losses.
See LICENSE filedistribution network reconfigurationquantum optimizationbranch-exchange encoding
This paper presents an any-dimensional PDE solver that trains machine learning models in lower dimensions and applies them directly to higher-dimensional PDEs in a zero-shot manner, under mathematical conditions based on symmetries.
See LICENSE filePDE solverany-dimensional learningzero-shot transfer
A digital simulation toolkit for physics-based generation of realistic STM images of material surfaces, supporting atomic-scale surface characterization while addressing the extreme noise sensitivity of scanning tunneling microscopy.
See LICENSE filescanning tunneling microscopymaterial surface imagingphysics-based image generation
This paper introduces a compact, model-agnostic Physics Adapter for few-shot transfer of coastal flood prediction surrogates to unseen regions, reducing the need for extensive target-region simulation data.
See LICENSE fileCoastal Flood PredictionPhysics-Guided LearningFew-Shot Transfer
PreVAE-Turb applies a pre-trained variational autoencoder to spatial compression for surrogate modeling of gyrokinetic plasma turbulence. The model is fine-tuned with physics-informed losses, including a Fourier-space spectral loss to enforce spectral accuracy.
See LICENSE filePlasma TurbulenceSurrogate ModelingVariational Autoencoder
The paper presents a low-dimensional, invertible latent representation for reduced-order modeling of droplet morphology, enabling reconstruction of fluid-interface states from sparse recordings across a device’s actuation range.
See LICENSE fileDroplet morphologyFluid interfacesReduced-order modeling
Systematically compares hard-constrained and soft-constrained physics-informed molecular machine learning on experimental data, examining how fundamental thermodynamic relations such as the Clapeyron equation are embedded into architectures or training losses for materials property prediction.
See LICENSE filePhysics-informed molecular MLClapeyron equationThermodynamic constraints
AECSF addresses Bayesian state estimation in high-dimensional nonlinear dynamical systems through adaptive ensemble conditional score filtering, targeting particle-weight collapse and preserving non-Gaussian posterior structure.
See LICENSE fileData AssimilationBayesian State EstimationDiffusion Filtering
AutoPDEBench benchmarks automated LLM-based research for designing neural PDE solvers, with attention to domain-specific challenges such as varying parameters and high-speed flows.
See LICENSE fileneural PDE solversLLM auto-researchphysical simulation benchmark
Uses explicit-ion molecular dynamics and charge-regulation Monte Carlo simulations to compute the interaction force between two spherical, charge-regulated amphoteric nanoparticles, addressing how adjustable surface ionization governs their electrostatic interaction behavior.
See LICENSE fileamphoteric nanoparticlescharge regulationmolecular dynamics
CI-PINN introduces a causal integral neural architecture for evolution equations and PDEs, explicitly modeling temporal dependence through a Volterra-type causal integral module that addresses a limitation of conventional pointwise space-time PINN representations.
See LICENSE fileevolution equationsphysics-informed neural networkscausal integral network
Co-PiLOT combines a generative encoder-decoder with physics-informed constraints to support inverse design of molecules, devices, and microstructures against expensive black-box simulators.
See LICENSE filephysics-informed machine learninginverse designlatent space optimization
This paper presents a quantum Carleman lattice Boltzmann scheme for fluid collision dynamics, using a multi-relaxation-time operator in a weighted Hermite moment basis to support coherent multi-step evolution.
See LICENSE fileLattice BoltzmannQuantum SimulationCarleman Linearization
PhiBE-Flow targets physical systems with stochastic evolution, generating continuous-time trajectories consistent with probability densities inferred from discrete observations by estimating the induced probability velocity field.
See LICENSE filecontinuous-time trajectory generationdiscrete observationsstochastic physical systems