CADFit uses IoU-driven hybrid optimization to incrementally fit and validate executable CadQuery construction programs (extrude, revolve, fillet, chamfer, Boolean) from watertight meshes, recovering editable parametric CAD. It is modality-agnostic (mesh, point cloud, image-to-3D) and directly relevant to CAE workflows.
NewCC BY-NC 4.0 (non-commercial; academic and research use only, commercial use requires author permission)Mesh-to-CADReverse EngineeringCadQuery
DeepCAD reframes CAD modeling as a sequence-generation problem, learns a latent space with an autoencoder and trains a latent GAN (WGAN-GP) for random generation and editing. It is the most-cited baseline in generative CAD and sits upstream of the design-to-simulation pipeline.
NewMIT LicenseGenerative CADGeometric Deep LearningCAD Sequence
A beginner-friendly PINN library with thorough Chinese docs and TensorFlow/PyTorch/JAX/PaddlePaddle backends - a common starting point for scientific machine learning and PDE solving.
NewGNU Lesser General Public License v2.1PINNBeginnerChinese Docs
Open-source FEM-based multiphysics framework; describes variational problems in UFL and auto-generates efficient C++ discretization code - a standard academic tool for solids and coupled physics, also a high-fidelity reference for surrogates.
Google Research's differentiable incompressible-flow solver in JAX; the whole time-stepping loop is differentiable and JIT-compilable on GPU/TPU. A PNAS 2021 learned-interpolation result reached ~80x/40x speedups at equal accuracy, but the project is now unmaintained - treat it as a research prototype and reference.
Fully auto-differentiable CFD solver built on JAX for CPU/GPU/TPU, focused on end-to-end differentiable fluid simulation that couples seamlessly with neural networks.
NewGNU General Public License v3.0JAXDifferentiable CFDDifferentiable Physics
Google's open-source NumPy-style numerical computing library built on XLA with autodiff and functional transformations (grad/jit/vmap/pmap) - the substrate behind differentiable solvers and neural operators.
An open-source physics engine maintained by Google DeepMind, pairing generalised coordinates with soft convex contact dynamics for robotics, biomechanics and reinforcement learning, with MJCF, MJX, MuJoCo Warp and the 4.0 release.
NewApache-2.0 for source code; CC BY 4.0 for documentation, images and videos in the doc directoryPhysics EngineContact DynamicsRobot Simulation
Open-source CFD solver as a physics-AI data backbone: principles, case structure, getting started, alternatives, cost accounting and failure boundaries.
NVIDIA's physics-ML framework (formerly Modulus, renamed in 2025), a PyTorch-based library for PINN, neural operators and physics-constrained training - architecture, versions, comparisons and failure boundaries.
ETH Zurich CAM lab's PDE foundation model and downstream fine-tuning suite, using semigroup augmentation to mine abundant training pairs and cover 15 downstream tasks with mesh-invariant inference.
NewNo LICENSE file in the repository; the official model weights are labelled CC BY-NC 4.0 on HuggingFace and marked as research modelsFoundation ModelNeural OperatorDownstream Tasks
Python 3D visualization and mesh-processing framework wrapping VTK; a concise API for field data, mesh rendering and animation. The de-facto standard for simulation post-processing, ML dataset construction and QA, used as the output layer by FEniCSx / PyMAPDL.
Open-source CFD and discrete-adjoint solver with built-in aerodynamic shape optimization; PDE-constrained gradients at a cost independent of design-variable count, a high-fidelity reference for surrogates.
NewGNU Lesser General Public License v2.1CFDAdjointShape Optimization
A Python-embedded parallel programming language for high-performance numerical computing, with LLVM JIT compilation of per-element kernels, sparse data structures and automatic differentiation, widely used for differentiable physics prototyping.
A physics-informed CNN whose loss encodes a finite-difference heat conduction residual, used as a surrogate for a liquid-cooled 21700 battery pack temperature field.
NewarXiv preprint (copyright held by authors)Thermal ManagementPINNBattery
An open-source seismic structural analysis framework originating at UC Berkeley, built on nonlinear fibre beams, shell elements and soil-structure interaction; through OpenSeesPy it supports scripted batch generation of earthquake response data for surrogate models and damage assessment.
NewCopyright The Regents of the University of California (1999-2020); free for non-commercial use by educational, research and non-profit entities, internal use only for other entities, commercial redistribution requires separate licensingOpenSeesEarthquake EngineeringNonlinear Analysis
A global medium-range weather forecasting model published by Huawei Cloud in Nature in 2023, whose 0.25 degree forecasts outperform the ECMWF operational IFS across all tested variables, with a five-day forecast taking about 1.4 seconds; weights are CC BY-NC-SA 4.0 and non-commercial.
NewTrained weights are CC BY-NC-SA 4.0 with commercial use forbidden; the repository ships no LICENSE file and declares no code licenseWeather Forecasting3D TransformerMedium-Range Forecasting
The reservoir-simulation example shipped in NVIDIA PhysicsNeMo, where a single X-MeshGraphNet sub-example implements a multiscale graph neural surrogate for full-field pressure and water saturation prediction on ECLIPSE/IX-compatible output. The entry pins down the real input and target formats, how error accumulates over autoregressive rollout steps, and the current state of dataset availability, which the upstream README still marks as forthcoming.
NewApache-2.0 for the PhysicsNeMo example repository; the Norne dataset carries its own licence termsReservoir SimulationGraph Neural NetworkMeshGraphNet
Deep reinforcement learning controls 19 magnetic coils of the Swiss TCV tokamak at 10 kHz to hold plasma shapes, snowflake divertor and droplet configurations, one of the most complete public sim-to-real control loops on fusion hardware.
NewPaper copyright retained by the authors; algorithm and libraries under their own open-source licensesFusionReinforcement LearningPlasma Control
TopoDiff, the conditional diffusion approach to structural topology optimization from the MIT DeCoDe Lab, with its 33,000-sample dual-level test protocol, surrogate guidance and per-metric definitions. This entry verifies what the eightfold and elevenfold claims actually refer to, and records inference cost, the 3D extension and follow-up work.
NewCC BY 4.0 for the arXiv version; published at AAAI 2023Topology OptimizationDiffusion ModelGenerative Design
Humanoid Robot Autonomy System / Sim-to-Real Motion Generation
Apple's open-code perceptive humanoid autonomy system: trained entirely in simulation and transferred to a Unitree G1, achieving 91% single-task success in unseen real homes.
NewApple proprietary license (non-OSI; GitHub marks Other/NOASSERTION; see repository LICENSE)Embodied AIHumanoid RobotSim-to-Real
Large-Scale Household Manipulation Simulation Framework / Generalist Robot Training and Benchmark
A large-scale household manipulation simulation framework from UT Austin and NVIDIA; the RoboCasa365 release ships 365 tasks across 2,500+ kitchen scenes with 600+ hours of human and 1,600+ hours of synthetic demonstrations for systematic benchmarking of generalist robot policies.
NewMIT (code); CC BY 4.0 (assets and datasets); embeds Apache-2.0 MuJoCo portionsRobot SimulationEmbodied AISynthetic Data
CAD Geometric Deep Learning Dataset / Parametric B-rep Ground-Truth Benchmark
A one-million CAD model dataset released at CVPR 2019, where every model is a collection of explicitly parametrized curves and surfaces providing ground truth for normals, curvature, patch segmentation and shape reconstruction; it is a core benchmark for geometric deep learning and generative CAD.
NewMIT for the dataset; CAD model copyright held by original creators; GPL for the processing pipelineCADGeometric Deep LearningB-rep
Embodied-AI Agent Framework / ROS 2 Robotics Development Framework
An open-source, vendor-agnostic agentic framework for Physical AI robotics from Robotec AI, built on ROS 2 so robots can understand natural language, plan and execute complex tasks, with voice interaction and simulation support.
Robot Kinematics and Dynamics Library / JAX Autodiff Control Framework
A pure-Python, JAX-based robot kinematics and dynamics library from Stanford ASL that delivers Pinocchio-class speed with autodifferentiation and MJX-compatible parallelism for high-performance IK and inverse-dynamics control.
Rigid-Body Dynamics Algorithm Library / Robot Kinematics and Dynamics Engine
A rigid-body dynamics library from Inria and LAAS-CNRS implementing Featherstone's algorithms with analytical derivatives, BSD-2-Clause licensed and used as the dynamics backbone of Crocoddyl, TSID, HPP, Aligator, Jiminy and many robotics frameworks.
NewBSD 2-Clause LicenseRigid Body DynamicsKinematicsRobot Control
GPU Rigid-Body Dynamics Solver / Heterogeneous-Batch Backend for the Newton Physics Engine
A GPU rigid-body dynamics solver open sourced by Skild AI with NVIDIA and contributed to the Newton physics engine, built for batches that mix different robots, tasks and worlds; the project reports 3.8x PhysX geometric-mean simulation throughput across 20 benchmarks.
NewApache-2.0 for Steel and Newton source code; CC BY 4.0 for Newton documentation and separate terms for bundled assetsRigid-Body DynamicsPhysics EngineRobot Simulation
Humanoid Whole-Body Control / Differentiable World Model Training Framework
An open-source humanoid whole-body control framework from UC Berkeley that amortizes learning across all motions with one differentiable world model, surpassing a 128-GPU, 7-day baseline in 3 hours on a single GPU and winning the CoRL 2026 Best Paper Award.
The deep learning protein structure prediction system released by DeepMind in 2021 and updated to v2.3.0 weights in 2024, containing monomer and multimer models, a full MSA search pipeline and Amber relaxation post-processing, with Apache-2.0 code.
NewCode is Apache-2.0; model parameters and CASP15 prediction data are CC BY 4.0Protein Structure PredictionDeep LearningMultiple Sequence Alignment
Materials and Chemistry / Atomistic Machine Learning
The consolidated repository of Meta FAIR Chemistry has grown from an OC20 electrocatalysis toolkit into a unified platform spanning molecules, materials, and catalysts, with the UMA model using a mixture-of-linear-experts architecture trained on 500 million structures and switching task names to serve seven domains from OC20 to OC25, OMat24, and OMol25.
NewRepository code is MIT (Meta, Inc.); the fairchem-lammps package declares GnuV2 on PyPI; UMA weights are licensed separately under gated model terms; datasets carry their own termsAtomic Foundation ModelMachine Learning PotentialElectrocatalysis
A global data-driven weather forecasting model proposed by NVIDIA and NERSC in 2022 that produces a week-long forecast at 0.25-degree resolution in under two seconds, matching ECMWF IFS at short lead times for large-scale variables and beating it for fine-scale fields, while making thousand-member large ensembles an inexpensive routine operation.
NewCode is BSD 3-Clause (Copyright (c) 2022, FourCastNet authors); data follows the Copernicus CDS terms; model weights ship with the repository distribution notesWeather ForecastingFourier Neural OperatorDeep Learning
A generative probabilistic weather model from Google DeepMind that uses a spherical diffusion model on a 0.25-degree grid to produce 15-day ensemble forecasts, generating one trajectory in 8 minutes and beating ECMWF ENS on 97.2% of 1320 evaluated targets; code is Apache-2.0 and the weights now permit commercial use.
NewApache-2.0 for code; model weights permit commercial use since August 2026, other materials CC BY 4.0Weather ForecastingProbabilistic ForecastingDiffusion Model
Google DeepMind's graph-network materials discovery system pushes the candidate pool past a billion structures through active learning, verifies them with DFT, and feeds the results back into training, adding 381,000 stable materials to the convex hull while shipping a downloadable convex-hull dataset and pretrained potential implementations.
NewCode and notebooks are Apache-2.0; the GNoME dataset is released under CC BY-NC 4.0 (non-commercial); the paper is CC BY 4.0Materials DiscoveryGraph Neural NetworkFirst Principles
A graph-neural-network medium-range weather forecasting model from Google DeepMind that outperforms the ECMWF operational deterministic system on 90 percent of 1380 verification targets and completes a 10-day global forecast in under a minute on a single accelerator, with code and weights now consolidated in the WeatherNext repository.
NewPaper is copyright of Science; code and notebooks are Apache-2.0, model weights permit commercial use since 2026-08-06, other materials are CC BY 4.0WeatherGraph Neural NetworkMedium-Range Forecasting
An open-source equivariant graph-neural-network potential framework from the Csanyi group that unifies atomic cluster expansion with high-order equivariant message passing, reaching high accuracy with only two interaction layers, and now shipping several generations of foundation weights (MACE-MP, MH, OMOL, POLAR) for out-of-the-box molecular dynamics of crystals, liquids, gases, surfaces and reactive systems.
NewMIT (code); some weights are released under the Academic Software License (ASL) for academic use onlyMolecular DynamicsMachine-Learned PotentialEquivariant Neural Network
A hybrid model coupling a differentiable atmospheric dynamical core with a neural parameterization end to end, matching ECMWF ensemble forecasts over 1 to 15 days and reproducing historical warming trends in 40-year AMIP simulations, at three to five orders of magnitude less compute.
NewCode is Apache-2.0; trained model weights are CC BY-SA 4.0Weather ForecastingHybrid Physics-Machine LearningDifferentiable Solver
A faithful, trainable PyTorch reproduction of AlphaFold2 from Columbia University's AQLab, paired with the OpenProteinSet sequence database, turning one-shot structure prediction into a trainable system.
NewCode is Apache-2.0; DeepMind pretrained parameters are CC BY 4.0 (relaxed from CC BY-NC 4.0 as of January 2022)Protein Structure PredictionDeep LearningOpen Source Reproduction
A seismic full waveform inversion benchmark from Los Alamos National Laboratory, with 12 datasets totalling 2.1 TB across interface, fault, style and CO2 storage structures, plus baselines for four deep learning methods and a cross-domain generalization study.
NewCode is BSD 3-Clause (Copyright (c) 2022, Los Alamos National Laboratory); data is CC BY-NC-SA 4.0GeophysicsInverse ProblemSeismic
The three-track network structure prediction system from the Baker Lab at the University of Washington, running 1D sequence, 2D distance map and 3D coordinate tracks in parallel, published in Science and open sourced in 2021; the code is MIT while the weights are limited to non-commercial research under the Rosetta-DL license.
NewCode is MIT; trained weights and data are under the Rosetta-DL software license for internal, non-commercial research use onlyProtein Structure PredictionThree-Track NetworkDeep Learning
Harvard CS249r open textbook series (four volumes) covering how ML systems are built - from foundations and scaling to agentic AI and physical AI - with runnable Python labs and teaching tools.
NewCC BY-NC-ND 4.0 (book text); CC BY-NC-SA 4.0 (labs/slides)TextbookML SystemsPhysical AI
An open-source PyTorch library from the UCLA Machine Intelligence Group that standardizes access to ERA5, CMIP6 and PRISM data, baseline models, metrics and visualizations for reproducible large-scale benchmarking of statistical downscaling and temporal forecasting.
High-performance molecular dynamics suite for biomolecular systems, with mature GPU acceleration and a built-in neural network potential interface - the mainstream open-source tool for protein, lipid and solvent simulation.
NewGNU Lesser General Public License 2.1Molecular DynamicsBiomoleculeGPU Acceleration
Open-source classical molecular dynamics engine from Sandia, covering materials and soft matter with multiscale modelling and custom potentials, plus ML-IAP interfaces for machine-learned potentials.
NewGNU General Public License 2.0Molecular DynamicsMaterials SimulationPotentials
A pandas-compatible distributed DataFrame library from UC Berkeley that runs the same pandas code across Ray, Dask or MPI clusters, used for large-scale simulation post-processing and surrogate-model data pipelines.
NewApache License 2.0DataFrameParallel ComputingBig Data
NVIDIA's open-source Python framework that JIT-compiles plain Python functions into CPU/CUDA kernels with automatic differentiable adjoints, letting gradients flow through entire physics simulations - the compute substrate under Isaac Lab and Newton.
High-performance scientific library from Argonne for large linear/nonlinear systems and parallel infrastructure - the underlying solver engine of top-tier CFD and multiphysics simulation, BSD-2-Clause friendly for commercial use.
GPU-Accelerated Humanoid / Digital-Human Motion Simulation and Learning Framework
An open-source GPU-accelerated simulation and learning framework from NVIDIA Labs for digital humans and humanoid robots, covering motion tracking, generative policies and sim-to-real deployment across IsaacGym, Isaac Lab, Newton and MuJoCo backends.
A PyTorch-based graph neural network library that unifies graph convolutions, heterogeneous graphs, point clouds and graph retrieval-augmented generation under one message-passing paradigm, used for mesh-based physics surrogates and molecular materials modelling.
A 1000-case steady RANS airfoil benchmark with data-efficiency, Reynolds and angle-of-attack extrapolation tasks, reviewed for its numerical setup, metric definitions and unverifiable accuracy claims.
NewODbL v1.0 for dataset and code; paper copyright retained by the authorsAerospace AerodynamicsAirfoilHigh-Fidelity CFD
The 500-variant DrivAer scale-resolving CFD dataset with 484 public runs, about 31 TB, official splits and geometry-extrapolation regimes, plus the surrogate regime it supports.
NewCC BY-SA 4.0 for the dataset; paper copyright retained by the authorsAutomotive AerodynamicsHigh-Fidelity CFDSurrogate Model
The NIST-led additive manufacturing benchmark series tests melt-pool, residual-stress and microstructure models through controlled machines, standardized artifacts and blind challenges, with nine benchmark sets and 85 challenge submissions in 2025.
NewPublic data (U.S. NIST, public domain)Additive ManufacturingMetal 3D PrintingBenchmark
Structural Health Monitoring / Damage Identification / Benchmark Dataset
The IASC-ASCE four-storey steel-frame SHM benchmark with its 12- and 120-DOF models and six damage patterns, reviewed alongside physics-informed damage identification methods, with corrections to earlier unverifiable claims.
NewVarious; paper copyright retained by the authors, data distributed under the task group termsStructural Health MonitoringDamage IdentificationBenchmark Dataset
A building-energy case built on EnergyPlus and its surrogate models, traced through the official documentation, the license file and the ORNL/UTK surrogate publications. The entry corrects the maintainer attribution, the release year and the way simulation fidelity and surrogate speed-up are usually quoted, then separates the quantitative claims a surrogate can actually support from the range where it stops being reliable.
NewEnergyPlus licence (BSD-style three-clause terms, name-use clause and retained U.S. Government rights)Building EnergyEnergyPlusHVAC
The open-source chemical kinetics suite originally initiated at Caltech and hosted under NumFOCUS provides thermodynamics, detailed kinetics, transport, zero-dimensional reactor networks and one-dimensional reacting flows in one object model, shipping 22 built-in mechanisms such as GRI-Mech 3.0 as a reproducible source of physical ground truth for combustion, electrochemistry and plasma modelling.
NewBSD 3-Clause style (California Institute of Technology 2001-2009, Sandia Corporation 2009, Cantera Developers 2011-2026)Canterachemical kineticscombustion
NVIDIA's open-source distributed algebraic multigrid library offers classical Ruge-Stuben and unsmoothed aggregation AMG, multiple smoothers and Krylov methods, with a reported two- to fivefold single-GPU speedup over a competitive CPU implementation.
Neural networks predict 0D reduced-order model parameters from vascular geometry, keeping the low cost and interpretability of the 0D model. Across aortic, aortofemoral and pulmonary patient-specific anatomies, mean pressure error drops by at least half, with the pulmonary cohort improving from 30.4% to 7.9%.
NewarXiv preprint (CC BY 4.0), copyright held by authorsHemodynamicsReduced OrderDigital Twin
A solver-independent reinforcement learning platform for flow control, providing 61 validated open-source 2D and 3D environments across six CFD solver backends including fully differentiable solvers. Its zero-shot transfer experiment deploys a channel-trained policy onto a 3D NACA0012 wing, cutting local skin friction by about 38% and total drag by about 11% while cutting exploration cost by four orders of magnitude relative to direct on-wing training.
General CFD / Industrial Simulation / Data Generation
A review of the industrial multiphysics pipeline around the three OpenFOAM distribution lines: conjugate heat transfer coupling, what version 14 and v2606 actually changed, the real state of GPU offloading, and where electromagnetic capability actually sits in the mainline code.
NewGPL-3.0 (all three distribution lines publish under GPL v3)OpenFOAMFinite VolumeIndustrial Simulation
Semiconductor TCAD surrogates anchored on two verifiable foundations: the fp_ddm sub-example in NVIDIA PhysicsNeMo, which applies overlapping Schwarz domain decomposition to a steady-state 2D heat-conduction problem against a plane-stress elasticity case, and the etch-process morphology surrogates reported by the SK hynix TCAD Intelligence team. The entry separates process-level TCAD from device-level electrical surrogates and records the accuracy and geometry-scaling limits of each.
NewApache-2.0 for the PhysicsNeMo repository; DAC 2026 paper copyright held by the authorsSemiconductorTCADDomain Decomposition
The PyBaMM battery modelling framework, read through its official documentation, source and release policy. The entry reconstructs the model lineage from SPMe to the DFN, the solver and parameter-set options, the version strategy and the engineering boundaries, and it corrects the common misreading that PyBaMM is a digital twin: it provides offline solving capability, and data assimilation and online state estimation sit outside the framework.
A gradient-based aerodynamic shape optimization workflow built on SU2's discrete and continuous adjoint routes, covering airfoil, wing and automotive shape parameterizations, gradient verification and measured drag reduction, usable as a teacher signal for surrogate training and as a high-fidelity reference.
NewGNU Lesser General Public License v2.1Aerodynamic OptimizationAdjoint MethodCFD
An open-source wave energy converter simulation framework led by NREL and Sandia, built on Simulink/Simscape Multibody with frequency-domain BEM hydrodynamics, convolution integrals and Morison elements, covering irregular waves, mooring and six-degree-of-freedom control, and providing reproducible time-domain ground truth for device design, control verification and surrogate model training.
NewApache-2.0 (Sandia LLC and NTESS, 2014, with certain rights retained by the U.S. Government under contract DE-NA0003525)Wave EnergyHydrodynamicsMultibody Simulation
Wind Energy / Multiphysics Simulation / Wake Control
A verifiable chain through OpenFAST aeroelastic simulation, the FAST.Farm multi-turbine wake model, the FLORIS engineering wake model and IEA Wind reference machines. This entry checks the origin of every quantitative claim and records where the chain breaks.
NewApache-2.0 for OpenFAST, FAST.Farm, FLORIS and the IEA Wind Task 55 reference modelsWind EnergyAeroelasticityWake Control
A four-ledger cost model for physics-AI surrogates: corpus generation, training, per-query inference and verification, with a reproducible break-even formula, the 2026 cost-accuracy frontier, the reversal at tight tolerances and hybrid warm-start deployment.
A decision-oriented review of neural operators: function-space contracts, four architecture families, six selection constraints, stress tests, a decision tree and an engineering checklist, with careful treatment of discretisation invariance and benchmark rankings.
A full-stack review of PINNs: composite-loss mechanics, five failure modes, 2026 progress, an actionable selection tree, a toolchain map and an engineering checklist, clarifying how PINNs differ from neural operators.
NewOriginal (DClaw)PINNPhysics-Informed Neural NetworksScientific ML
PythonRobotics, maintained by Atsushi Sakai, is a Python code collection and online textbook of robotics algorithms - covering localization, mapping, SLAM, motion planning, path tracking and arm navigation - and a de-facto reference for robotics beginners thanks to its minimal-dependency, readable implementations.
370 multi-hop high-school physics questions, each paired with a complete step-by-step solution, used to evaluate LLM physics reasoning - the evaluation set accompanying the TrustAgent method (AAAI 2026).
A Chinese structured tutorial implementing PINN from minimal dependencies, built chapter by chapter around the 1D heat equation — ML basics, separation of variables, FDM/FEM comparisons, PINN model construction and optimizer comparison, GMM and curriculum learning, plus locELM, random-feature and RaNN extensions. MIT licensed - the best start for Chinese-speaking learners.
LeVeque team finite-volume package - Godunov-type schemes for hyperbolic conservation laws, standard tool for shocks, tsunami, reservoir, and seismic waves.
Python framework that builds spectral-method solvers symbolically (Burns et al. 2020), widely used in fluid dynamics, plasma, star and planet research.
FEM platform where you write variational forms in near-math UFL syntax and discretization/solving is automated - the standard learning route with its official tutorial book.
Julia SciML ecosystem library unifying PINN/DeepONet/NeuralOperator solvers with seamless DifferentialEquations.jl interoperability and GPU/autodiff out of the box.
NVIDIA open-source physics-AI training/inference framework (formerly Modulus) with official examples across CFD, structural, EM, weather, and semiconductor TCAD.
The Python analysis library behind Materials Project - crystal structures, phase diagrams, band structures, DOS out of the box; the standard data layer between DFT and ML workflows.
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