Browse Categories

Filter all entries by physics domain, license and release year. Multiple picks within a group mean "any of"; across groups they combine with "and".

Physics domain
License
Release year

551 results

ABC Dataset: A Million-Scale Parametric CAD Benchmark

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.
New MIT for the dataset; CAD model copyright held by original creators; GPL for the processing pipeline CADGeometric Deep LearningB-rep

AirfRANS

Fluid / CFD - Airfoil RANS
Parametric airfoil RANS flow-field dataset - compact and ML-pipeline friendly, the go-to starting point for learning fluid surrogates.
ODbL CFDAirfoilRANS

CFDBench

CFD Benchmark / Multi-Scenario
Multiphysics benchmark for computational fluid dynamics covering internal/external flows and thermal convection - includes transient and steady-state data.
See LICENSE file CFDFluidThermal Convection

PES2O Materials Science Pretraining Corpus 780M

Materials
A large-scale pretraining corpus for materials science, containing approximately 780M tokens of RefinedWeb data, designed for training AI models for materials discovery and molecular dynamics research.
See LICENSE file materials sciencepretraining corpusAI materials discovery

32wind-CFD Dataset

CFD/Computational Fluid Dynamics
A computational fluid dynamics dataset hosted on HuggingFace, focusing on wind-related fluid simulation data for CFD researchers and engineers.
apache-2.0 computational fluid dynamicswind simulationCFD dataset

CFD Benchmark Dataset

CFD/Computational Fluid Dynamics
A comprehensive benchmark dataset for training and evaluating neural PDE solvers, containing six standard tasks on regular grids, structured grids, and irregular geometries, used for unified evaluation in the ICML 2024 paper Transolver.
other Neural PDE SolverCFDBenchmark Dataset

MaCroScope-Physics-10k Physical Macroscopic Dataset

ScientificML
MaCroScope physical macroscopic dataset with 10k samples for machine learning training and evaluation in physics-related scenarios.
See LICENSE file macroscopic microscopyphysical datasetmachine learning

CFDBench: Computational Fluid Dynamics Benchmark Dataset

CFD/Computational Fluid Dynamics
A large-scale benchmark dataset for machine learning in computational fluid dynamics, covering four classic CFD problems—lid-driven cavity, laminar pipe flow, dam-break, and flow around a cylinder—to evaluate neural operator generalization under unseen conditions.
apache-2.0 computational fluid dynamicsbenchmark datasetneural operators

Adaption Materials Science QA Augmented Dataset

Materials
A technical Q&A dataset covering fundamental and advanced topics in materials science, including material properties, synthesis methods, characterization techniques, and engineering applications, designed for training technical response models.
See LICENSE file materials sciencetechnical Q&Asynthesis methods

Materials Platform for Data Science

Materials
A comprehensive materials science dataset with ~500K peer-reviewed publications, 139K phase diagrams, 409K crystalline nanostructures, and 1M+ physical property sets, enabling computational materials design and ML-driven materials informatics research.
See LICENSE file Materials ScienceCrystal StructurePhase Diagram

MaCroScope-Physics-5k Dataset

ScientificML
A HuggingFace-hosted machine learning dataset for physics domain, part of the MaCroScope series, with Physics-5k containing approximately 5000 samples.
See LICENSE file datasetphysics machine learningMaCroScope

interpolant_pdes Dataset

ScientificML
A HuggingFace dataset repository related to PDE interpolants, supporting research at the intersection of physics modeling and machine learning.
See LICENSE file PDEinterpolantdataset

CFD Surrogate Data

CFD Surrogate
A HuggingFace-hosted dataset repository for computational fluid dynamics surrogate modeling, containing data resources for CFD simulation and surrogate model development.
apache-2.0 Computational Fluid DynamicsSurrogate ModelDataset

FuXi-CFD Dataset

Computational Fluid Dynamics
A large-scale CFD-generated wind field simulation dataset containing over 12,000 cases, designed for training and evaluating terrain-informed machine learning models to reconstruct fine-scale 3D wind fields
See LICENSE file CFDwind field simulationmachine learning

MaCroScope Physics 20k Cleaned Dataset

ScientificML
A cleaned version of the MaCroScope physics-related experimental dataset with approximately 20k entries, hosted on HuggingFace for research purposes.
See LICENSE file datasetphysics experimentMaCroScope

FuXi-CFD Wind Field Dataset

CFD
Large-scale CFD-generated wind field dataset with over 12,000 cases, designed for training and evaluating the terrain-informed machine learning model FuXi-CFD for fine-scale 3D wind field reconstruction.
See LICENSE file wind field simulationCFDmachine learning

PDECert Natural-Candidate Pilot Benchmark

ScientificML
A provenance-bearing benchmark for verifying symbolic candidate solutions to PDEs, containing 20 records with generator outputs, verification cases, and human annotations for assessing symbolic solver reliability.
See LICENSE file PDESymbolic SolvingBenchmark

LeRobot Arm Test Dataset

Multibody/Robotics
A robot arm manipulation dataset collected using the LeRobot framework, containing 51 episodes and 29803 frames of video data for robot manipulation policy learning.
See LICENSE file robot datasetrobot armLeRobot

Materials Sciences Demo Dataset

Materials
A materials science demonstration dataset hosted on HuggingFace under the SciFy account, showcasing data organization and access patterns for materials science applications.
See LICENSE file Materials ScienceDatasetHuggingFace

MaCroScope-Physics-1k Dataset

ScientificML
MaCroScope-Physics-1k is a physics-related scientific dataset published by the ai4collaboration team, designed to support research at the intersection of physical modeling and machine learning.
See LICENSE file datasetphysics sciencemachine learning

GeoPT Downstream Physics Simulation Dataset

CFD
A physics simulation dataset accompanying the GeoPT paper, covering 5 downstream tasks including aerodynamic simulations, with metadata on mesh sizes, variables, and train/test splits.
See LICENSE file physics simulation datasetgeometric pre-trainingaerodynamic simulation

Cross-Representation PDE Evaluation Dataset

ScientificML
A PDE evaluation dataset containing 32 physical systems, each with four representations: source code, natural-language description, governing equation, and numerical trajectory, with both correct and corrupted variants.
See LICENSE file PDE evaluationcross-representation learningphysical systems

CFD Surrogate Data

Computational Fluid Dynamics
A computational fluid dynamics surrogate model training dataset hosted on HuggingFace by user harryshah14.
See LICENSE file Computational Fluid DynamicsSurrogate ModelCFD Dataset

Science Materials Dataset

Materials
A materials science dataset hosted on HuggingFace, supporting machine learning and materials science cross-disciplinary research, containing relevant domain training or evaluation samples.
See LICENSE file Materials ScienceDatasetMachine Learning

SPUS PDE-UNet-36M Navier-Stokes PWC Model

CFD
A 36M-parameter UNet-based model for solving Navier-Stokes equations using a point-wise coupling strategy for high-accuracy flow field prediction.
See LICENSE file Navier-StokesPDE SolvingUNet

Materials Science and Engineering Domain Ontologies

Materials
A collection of domain ontologies for materials science and engineering, providing semantic organization of core concepts including structure, properties, processing, and performance for knowledge reasoning applications.
See LICENSE file Materials ScienceOntologyKnowledge Graph

PDE Surrogate Benchmark Dataset

ScientificML
A benchmark dataset for PDE surrogate tasks within the ai4sci-tasks evaluation framework, containing training trajectories and evaluation splits for assessing neural operator and surrogate modeling performance.
See LICENSE file PDE SurrogateBenchmark DatasetScientific ML

MaCroScope-Physics-4k Dataset

ScientificML
MaCroScope-Physics-4k is a physics-related dataset hosted by ai4collaboration on HuggingFace, with the name suggesting approximately 4,000 samples, potentially for machine learning and physics modeling research.
See LICENSE file datasetphysics sciencemachine learning

PDEControl_DPC - TI-DeepONet Training Datasets

ScientificML
Simulation training datasets for PDE control containing 3000 controlled trajectories generated by classical numerical solvers under randomly sampled control sequences, designed for training TI-DeepONet surrogate models.
See LICENSE file PDE controlDeepONetNeural operator

cluster-03-potential-flow-pinn Model

Physics-Informed Neural Networks
A HuggingFace repository containing a potential flow PINN clustering model, providing physics-informed neural network resources for potential flow modeling.
mit Physics-Informed Neural NetworksPotential FlowClustering

Downstream_Physics_Simulation Dataset

ScientificML
A downstream physics simulation dataset accompanying the GeoPT paper, containing multi-scale mesh data across 5 simulation tasks to validate the generalization of geometric pre-trained neural simulation models across diverse physics domains.
See LICENSE file physics simulation datageometric pre-trainingneural simulation

PDE Solver Code Perturbation Evaluation Dataset

ScientificML
A code perturbation dataset with 256 PDE solver implementations comprising 64 base programs and 4 lexical perturbation variants each, designed for evaluating LLM understanding of physics simulation code.
See LICENSE file PDE solvercode perturbationLLM evaluation

FM4PDE PDE Dataset

ScientificML
A public dataset for partial differential equation modeling, providing data resources for physics-field simulation and machine learning model training.
See LICENSE file Partial Differential EquationsPhysics DatasetScientific Machine Learning

PDE-OBS Numerical PDE Record Dataset

ScientificML
PDE-OBS provides complete numerical solutions for seven families of partial differential equations in the PDE-OBS benchmark, including stationary Darcy, Poisson, and Helmholtz equations and heat-related PDEs.
See LICENSE file Partial Differential EquationsNumerical SolutionsScientific Machine Learning

PDE-OBS Partial Differential Equation Benchmark Dataset

ScientificML
A benchmark dataset of complete numerical solutions for seven PDE families including Darcy, Poisson, and Helmholtz, generated by the benchmark's own solvers for scientific ML model evaluation.
See LICENSE file PDE benchmarknumerical solution datasetscientific ML

DrivAerNet++

Automotive Aerodynamics / Large-Scale CFD
MIT's large-scale automotive aerodynamics dataset: 8,000 parametric car geometries with CFD flow fields, meshes and aerodynamic coefficients.
Creative Commons Attribution-NonCommercial 4.0 AutomotiveAeroCFD

PDEArena

PDE Benchmark / Differentiable Solver
Microsoft Research's open-source PDE benchmark suite with differentiable solvers and spatiotemporal dynamics data for evaluating long-horizon rollout stability.
MIT PDEBenchmarkDifferentiable Solver

PDEBench

PDE Benchmark / Multi-Equation
Large-scale PDE benchmark covering heat, advection-diffusion and fluid dynamics - supports fair comparison of data-driven and physics-informed methods.
MIT License BenchmarkPDECFD

PhysicsQA Reasoning Dataset

ScientificML
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).
New Apache-2.0 Physics Q&APhysics AIReasoning Evaluation

PLAID

Industrial Heterogeneous-Mesh Simulation
ICML 2026 industrial physics-ML dataset with 6 heterogeneous-mesh simulation sets, CGNS-compatible, distributed via HF+Zarr - closest to real CAE workflows.
BSD 3-Clause License IndustrialHeterogeneous MeshCGNS

The Well

Multiphysics / PDE - 16 Domains
Unified benchmark spanning 16 physical domains, dubbed the 'ImageNet moment of physical ML', with PyTorch API, pretrained baselines and HF streaming.
Per subset (mostly CC-BY / code MIT) MultiphysicsBenchmarkPyTorch

TIDE

3D Turbulence (DNS Validation)
2026 3D turbulent DNS benchmark with 5 tasks and controlled generalization splits, designed to test extrapolation of turbulence models.
MIT License TurbulenceDNS3D

TU Delft Vertical-Axis Wind Turbine Array Wake Dataset

Turbulent Wake / Experimental Measurement & CFD Validation
Three-dimensionally resolved wake fields of a 3x3 array of nine H-type vertical-axis wind turbines, measured by volumetric particle tracking velocimetry in TU Delft's open-jet wind tunnel for baseline, pitch-in and pitch-out cases - an experimental benchmark for turbulent wakes and wake control.
CC BY 4.0 TurbulenceWakeBluff-Body Flow

U-bend Parametric Thermal-Fluid Dataset

Conjugate Heat Transfer / Parametric Simulation
10,000 parametric U-bend conjugate-heat-transfer simulations from the University of Kassel, each defined by 28 design parameters and offered in three representations (parameter vectors, multi-resolution 2D images, mesh cell values) for heat-exchanger shape optimization and surrogate modeling.
CC BY-NC 4.0 Heat ExchangerBendThermal Coupling

CADFit: Precise Mesh-to-CAD Program Generation with Hybrid Optimization

Mesh-to-CAD / Reverse Engineering
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.
New CC BY-NC 4.0 (non-commercial; academic and research use only, commercial use requires author permission) Mesh-to-CADReverse EngineeringCadQuery

ClimateLearn: Benchmarking Machine Learning for Weather and Climate

Climate ML Benchmarking Library
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.
New MIT ClimateMachine LearningBenchmark

DeepCAD: A Deep Generative Network for Computer-Aided Design Models

Generative CAD / Geometric Deep Learning
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.
New MIT License Generative CADGeometric Deep LearningCAD Sequence

DeepXDE

PINN Starter Framework
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.
New GNU Lesser General Public License v2.1 PINNBeginnerChinese Docs

FEniCS / FFCx

Finite Element Framework / Multiphysics
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.
New LGPL-3.0 FEMFinite ElementMultiphysics

Frax

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.
New MIT License Robot DynamicsKinematicsAutomatic Differentiation

HALO

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.
New Apple proprietary license (non-OSI; GitHub marks Other/NOASSERTION; see repository LICENSE) Embodied AIHumanoid RobotSim-to-Real

GROMACS

Molecular Dynamics Simulation Suite
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.
New GNU Lesser General Public License 2.1 Molecular DynamicsBiomoleculeGPU Acceleration

JAX-CFD

Differentiable Fluid Solver
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.
New Apache-2.0 JAXDifferentiable PhysicsCFD

JAX-Fluids

Differentiable CFD Solver
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.
New GNU General Public License v3.0 JAXDifferentiable CFDDifferentiable Physics

JAX

Differentiable Numerical Computing Framework
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.
New Apache License 2.0 Automatic DifferentiationXLANumerical Computing

LAMMPS

Molecular Dynamics Simulator
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.
New GNU General Public License 2.0 Molecular DynamicsMaterials SimulationPotentials

Modin

Distributed DataFrame Library
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.
New Apache License 2.0 DataFrameParallel ComputingBig Data

MuJoCo

General-Purpose Physics Engine / Contact Dynamics Solver and Robotics Simulation Backend
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.
New Apache-2.0 for source code; CC BY 4.0 for documentation, images and videos in the doc directory Physics EngineContact DynamicsRobot Simulation

NeuralOperator

Neural Operator Library
Reference PyTorch library for FNO, TFNO and DeepONet: function-space contracts, parameters, getting started, failure modes and cross-resolution evaluation.
New MIT Neural OperatorFNODeepONet

NVIDIA Warp

Differentiable GPU Simulation Framework
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.
New Apache License 2.0 Differentiable SimulationGPUJIT Compilation

OpenFOAM

General-Purpose CFD Solver
Open-source CFD solver as a physics-AI data backbone: principles, case structure, getting started, alternatives, cost accounting and failure boundaries.
New GPL v3 CFDOpen SourceSolver

PETSc

Numerical Solver Library / HPC
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.
New BSD-2-Clause SolverLinear AlgebraSparse Matrix

PhysicsNeMo

Solver / Training Framework
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.
New Apache-2.0 PINNNeural OperatorNVIDIA

Pinocchio

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.
New BSD 2-Clause License Rigid Body DynamicsKinematicsRobot Control

POSEIDON

PDE Foundation Model / Downstream Benchmark
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.
New No LICENSE file in the repository; the official model weights are labelled CC BY-NC 4.0 on HuggingFace and marked as research models Foundation ModelNeural OperatorDownstream Tasks

NVIDIA ProtoMotions

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.
New Apache License 2.0 Physics SimulationHumanoid RobotMotion Generation

PyTorch Geometric

Graph Neural Network Framework
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.
New MIT License Graph Neural NetworkMessage PassingPyTorch

PyVista

Visualization / Post-Processing
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.
New MIT VisualizationVTKMesh

RAI

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.
New Apache License 2.0 Embodied AIAgent FrameworkROS 2

RoboCasa

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.
New MIT (code); CC BY 4.0 (assets and datasets); embeds Apache-2.0 MuJoCo portions Robot SimulationEmbodied AISynthetic Data

Steel

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.
New Apache-2.0 for Steel and Newton source code; CC BY 4.0 for Newton documentation and separate terms for bundled assets Rigid-Body DynamicsPhysics EngineRobot Simulation

SU2

Aerodynamics / Design Optimization Solver
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.
New GNU Lesser General Public License v2.1 CFDAdjointShape Optimization

SuperMimic

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.
New Apache License 2.0 Physics SimulationHumanoid RobotMotion Imitation

Taichi Lang

Physics Simulation DSL
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.
New Apache License 2.0 Physical SimulationDifferentiable ProgrammingDSL

PINN Heat Equation Solver

PINN
A heat conduction equation solver based on Physics-Informed Neural Networks, using neural networks embedded with heat conduction physics to predict temperature fields.
See LICENSE file Physics-Informed Neural NetworksHeat EquationHeat Conduction

cluster-02-hydrostatic-pinn

PINN Model
A HuggingFace repository hosting a Physics-Informed Neural Network model for hydrostatic fluid mechanics computations, applying physics-based constraints to deep learning approaches.
mit Physics-Informed Neural NetworksHydrostaticsDeep Learning

DeepXDE v1.15.0

PDE Solving
DeepXDE v1.15.0 released with L-LAAF activation function support for JAX backend and Apple MPS GPU acceleration for PyTorch backend, improving deep learning-based PDE solving performance.
LGPL-2.1 PDEDeep LearningScientific Computing

OneScience-Group/PINN-TC

Scientific Computing
A PINN-related model resource hosted on HuggingFace by OneScience-Group, designed for scientific computing and physics-based problem modeling.
cc-by-4.0 Scientific ComputingNeural NetworksPhysics-Informed Neural Networks

FEniCS/dolfinx v0.11.0.post0 Released

Scientific Computing/Finite Element
FEniCS/dolfinx releases a patch version that fixes a Mathjax rendering issue in the built documentation. This release is functionally identical to v0.11.0, so users do not need to upgrade.
GNU Lesser General Public License v3.0 FEniCSdolfinxFinite Element

Unitree UnifoLM-WLA-1.0 General-Purpose Humanoid Robot Foundation Model

Embodied AI / Robot Foundation Model
Unitree releases UnifoLM-WLA-1.0, a 6B parameter general-purpose embodied AI model trained with ~2500 hours of real-machine data, achieving 7 open-source SOTA results in embodied reasoning.
See LICENSE file embodied AIhumanoid robotfoundation model

Spherical Fourier Neural Operators

Neural Operator
A neural operator model based on spherical Fourier transforms, designed for learning partial differential equations on spherical geometries.
other Neural OperatorFourier Neural OperatorSpherical Data

Neural Operator Predictors for Sampled Measurements

Neural Operator
A neural operator-based predictor model hosted on HuggingFace, designed for sampled measurement prediction tasks.
See LICENSE file Neural OperatorScientific Machine LearningSampled Measurements

PhysicsNeMo v2.2.2

Physics Simulation
NVIDIA PhysicsNeMo v2.2.2 release fixes documentation alignment with the PyPi package name, improving installation accuracy.
Apache License 2.0 NVIDIAPhysics SimulationDeep Learning

NeuralOperator v2.0.0 Release

Scientific Computing
NeuralOperator 2.0.0 major release introduces Codano model, improves documentation, and enhances usability for training Neural Operators in PyTorch.
MIT License Neural OperatorDeep LearningPyTorch

Fundamental Physics Neural Operators

Neural Network / AI for Science
A fundamental physics neural operator model project published by Delta Lab on HuggingFace. Refer to official repository documentation for specific functionality and performance details.
mit Neural OperatorsFundamental PhysicsDelta Lab

Compressible Euler Equations PINN Model

PINN
A Physics-Informed Neural Network model for solving compressible Euler equations, hosted on HuggingFace.
mit Physics-Informed Neural NetworksComputational Fluid DynamicsCompressible Flow

cluster-07-fourier-pinn

Fourier-PINN
A HuggingFace model repository with a name suggesting Fourier-enhanced Physics-Informed Neural Networks implementation.
mit PINNFourierPhysics-Informed Neural Networks

AstroGenesis: A Domain-Specific Multi-Agent AI for Astrophysical Research

Astrophysics
A domain-specific multi-agent AI framework for astrophysical research that combines literature retrieval, multiwavelength data access and analysis, theoretical modeling, and research ideation within a unified environment, with its current implementation focused on blazar research.
See LICENSE file AstrophysicsMulti-Agent AIBlazar Research

CIFGS/physics-informed-sirenMRI-model

Physics-Informed Neural Networks
A physics-informed neural network model hosted on HuggingFace, with name suggesting relevance to MRI imaging and SIREN architecture; detailed information requires consulting the official page.
mit PINNMRISIREN

NVIDIA Earth-2: AI-Powered Weather Decision Platform

CFD
NVIDIA Earth-2 leverages AI atmospheric models integrated with observation data to provide high-resolution weather forecasts and decision support for weather-sensitive industries.
See LICENSE file weather forecastingatmospheric modelingAI meteorology

Physics-informed Neural Network CFD

Physics-informed Neural Network / CFD
A HuggingFace repository hosting a physics-informed neural network model for computational fluid dynamics, implementing physics constraints embedded within neural network architectures.
See LICENSE file PINNCFDphysics-informed neural network

SPUS-PDE-UNet-36M: Neural PDE Solver with 36M Parameters

ScientificML
A 36M-parameter neural network solver for partial differential equations based on U-Net architecture, enabling data-driven solving and prediction of PDE systems
See LICENSE file PDE solverneural networkU-Net

CompFlowLab: A Python Environment for Developing Data-Driven Compressible Flow Models

CFD
CompFlowLab is an open-source Python environment for data-driven modeling of compressible flow problems, including shocks, flames, and detonation waves. It combines a one-dimensional compressible Navier-Stokes solver with multispecies transport and chemical-reaction models for lightweight prototyping and evaluation.
See LICENSE file Compressible FlowData-Driven ModelingChemical Reaction Flows

Context-Conditioned Molecule Transfer Model for Carcinogens

ScientificML
A deep learning-based context-conditioned molecule transfer model designed for carcinogen-related molecular structure migration and generation in cheminformatics.
See LICENSE file molecule transferchemistry discoverymolecular generation

DMD-Neural-Operator

Scientific Computing
A scientific computing model on HuggingFace that integrates Dynamic Mode Decomposition with Neural Operator for scientific data modeling and prediction tasks.
mit Dynamic Mode DecompositionNeural OperatorScientific Computing

cluster-06-bubble-dynamics-pinn

PINN Model
A HuggingFace-hosted model repository for bubble dynamics using Physics-Informed Neural Networks (PINN), with the model name indicating focus on PINN-based bubble dynamics applications.
mit bubble dynamicsphysics-informed neural networksPINN

InternS1-Mini Context-Conditioned Molecule Transfer Model

Quantum/Chemistry
A context-conditioned molecule transfer model based on InternS1-Mini, designed for drug-induced liver injury (DILI) related molecular transformation tasks in chemical reaction prediction and drug discovery.
See LICENSE file molecule transferdrug discoverychemical reaction prediction

PDE-OBS Partial Differential Equation Model

ScientificML
This Hugging Face repository hosts the pdeobs-model resource under PDE-OBS, targeting scientific machine-learning workflows based on partial differential equations. The source listing provides no details about the model architecture, training data, benchmarks, or reported performance.
See LICENSE file Partial Differential EquationsScientific Machine LearningModel Resource

Sentinel Mumbai Hybrid PINN Model for Keras

ScientificML
A Hugging Face model resource for a hybrid physics-informed neural network targeting a Mumbai scenario and implemented with Keras for scientific machine learning.
See LICENSE file Physics-informed neural networkHybrid PINNKeras model

Sentinel Mumbai PINN v1

Scientific ML
A physics-informed neural network model for general scientific-computing physical fields, combining physical constraints with machine learning for physical modeling.
See LICENSE file Physics-Informed Neural NetworkScientific ComputingPhysical Modeling

AirfRANS High-Fidelity Airfoil Surrogate Benchmark Case

Aerospace Aerodynamics / High-Fidelity Dataset / Surrogate Evaluation
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.
New ODbL v1.0 for dataset and code; paper copyright retained by the authors Aerospace AerodynamicsAirfoilHigh-Fidelity CFD

AlphaFold: A Deep Learning System for Protein Three-Dimensional Structure Prediction

Biomedical / Structure Prediction
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.
New Code is Apache-2.0; model parameters and CASP15 prediction data are CC BY 4.0 Protein Structure PredictionDeep LearningMultiple Sequence Alignment

DrivAerML High-Fidelity Road-Car Aerodynamics Dataset and Surrogates

Automotive Aerodynamics / High-Fidelity Dataset / Surrogate Modeling
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.
New CC BY-SA 4.0 for the dataset; paper copyright retained by the authors Automotive AerodynamicsHigh-Fidelity CFDSurrogate Model

Physics-Informed CNN for Battery Pack Temperature Fields

Thermal Management / Physics-Informed ML
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.
New arXiv preprint (copyright held by authors) Thermal ManagementPINNBattery

NIST AM Bench Additive Manufacturing Benchmark

Additive Manufacturing / Benchmark Dataset
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.
New Public data (U.S. NIST, public domain) Additive ManufacturingMetal 3D PrintingBenchmark

IASC-ASCE Structural Health Monitoring Benchmark and Physics-Informed Damage Identification

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.
New Various; paper copyright retained by the authors, data distributed under the task group terms Structural Health MonitoringDamage IdentificationBenchmark Dataset

Building Energy Simulation and Surrogates: The EnergyPlus Case

Building Energy / Simulation Acceleration
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.
New EnergyPlus licence (BSD-style three-clause terms, name-use clause and retained U.S. Government rights) Building EnergyEnergyPlusHVAC

Cantera Reacting Flows and Chemical Kinetics in a Physics-AI Workflow

Combustion / Chemical Kinetics
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.
New BSD 3-Clause style (California Institute of Technology 2001-2009, Sandia Corporation 2009, Cantera Developers 2011-2026) Canterachemical kineticscombustion

How to Use AI Agents to Prepare 3D Scenes for Simulation

AI Simulation
This NVIDIA blog post describes how agentic AI workflows can be used to prepare and validate digital twins for physical AI systems, with agents capable of inspecting 3D scenes and authoring simulation-relevant data.
See LICENSE file AI AgentDigital Twin3D Simulation

AMGX GPU-Accelerated Algebraic Multigrid Solver

HPC / Solver
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.
New BSD 3-Clause License (NVIDIA Corporation, 2017-2024) AMGXAlgebraic MultigridGPU Acceleration

NVIDIA Earth-2 Industrial Climate Prediction Platform

Geophysics
NVIDIA Earth-2 enables weather-sensitive industries like energy to make timely decisions by integrating observational data with AI-powered atmospheric simulation.
See LICENSE file Climate SimulationWeather PredictionAtmospheric Physics

FAIR Chemistry and UMA: A Cross-Domain Atomic Foundation Model Platform

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.
New Repository 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 terms Atomic Foundation ModelMachine Learning PotentialElectrocatalysis

FourCastNet: Global Weather Forecasting with Adaptive Fourier Neural Operators

Weather / Data-Driven Forecasting
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.
New Code is BSD 3-Clause (Copyright (c) 2022, FourCastNet authors); data follows the Copernicus CDS terms; model weights ship with the repository distribution notes Weather ForecastingFourier Neural OperatorDeep Learning

GenCast: Diffusion-Based Ensemble Weather Forecasting on the Sphere

Probabilistic Ensemble Weather Forecasting Model
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.
New Apache-2.0 for code; model weights permit commercial use since August 2026, other materials CC BY 4.0 Weather ForecastingProbabilistic ForecastingDiffusion Model

GNoME: Scaling Materials Discovery from Ten-Thousand-Scale Enumeration to Million-Scale Convex Hulls

Materials Science / First Principles
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.
New Code and notebooks are Apache-2.0; the GNoME dataset is released under CC BY-NC 4.0 (non-commercial); the paper is CC BY 4.0 Materials DiscoveryGraph Neural NetworkFirst Principles

GraphCast: Graph Neural Networks for Global Medium-Range Weather Forecasting

Weather / Data-Driven Forecasting
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.
New Paper 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 4.0 WeatherGraph Neural NetworkMedium-Range Forecasting

Patient-Specific Hemodynamics via Hybrid Physics-Neural Surrogates

Biomedical Flow / Reduced-Order Modeling
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%.
New arXiv preprint (CC BY 4.0), copyright held by authors HemodynamicsReduced OrderDigital Twin

HydroGym: A Reinforcement Learning Benchmark Platform for Flow Control

Flow Control / Active Flow Control
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.
New MIT (code) / Nature paper Flow ControlReinforcement LearningDrag Reduction

MACE Machine-Learned Potentials: From Equivariant Message Passing to Atomistic Foundation Models

Molecular Dynamics / Machine-Learned Interatomic Potentials
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.
New MIT (code); some weights are released under the Academic Software License (ASL) for academic use only Molecular DynamicsMachine-Learned PotentialEquivariant Neural Network

NeuralGCM: A Hybrid Atmospheric General Circulation Model with a Differentiable Dynamical Core

Weather / Hybrid Physics-Machine Learning
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.
New Code is Apache-2.0; trained model weights are CC BY-SA 4.0 Weather ForecastingHybrid Physics-Machine LearningDifferentiable Solver

OpenFOAM Industrial Multiphysics Pipeline: From Meshing to Data Supply

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.
New GPL-3.0 (all three distribution lines publish under GPL v3) OpenFOAMFinite VolumeIndustrial Simulation

OpenFold: A Trainable PyTorch Reproduction of AlphaFold2

Biomedical / Structure Prediction
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.
New Code 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

OpenFWI: Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion

Geophysics / Inverse Problems
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.
New Code is BSD 3-Clause (Copyright (c) 2022, Los Alamos National Laboratory); data is CC BY-NC-SA 4.0 GeophysicsInverse ProblemSeismic

OpenSees Seismic Structural Simulation from Nonlinear Fibres to ML-Based Damage Assessment

Civil Engineering / Structural Simulation
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.
New Copyright 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 licensing OpenSeesEarthquake EngineeringNonlinear Analysis

Pangu-Weather: A 3D Earth-Specific Transformer for Global Medium-Range Weather Forecasting

Weather / Data-Driven Forecasting
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.
New Trained weights are CC BY-NC-SA 4.0 with commercial use forbidden; the repository ships no LICENSE file and declares no code license Weather Forecasting3D TransformerMedium-Range Forecasting

Graph Neural Surrogates for Reservoir Simulation: PhysicsNeMo X-MGN

Geophysics / Reservoir Engineering
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.
New Apache-2.0 for the PhysicsNeMo example repository; the Norne dataset carries its own licence terms Reservoir SimulationGraph Neural NetworkMeshGraphNet

Semiconductor TCAD Surrogates: FP-DDM Domain Decomposition and Etch Process Surrogates

Semiconductor / Device and Process 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.
New Apache-2.0 for the PhysicsNeMo repository; DAC 2026 paper copyright held by the authors SemiconductorTCADDomain Decomposition

The PyBaMM Battery Modelling Framework: From Expression Trees to Experiment Protocols

Energy Storage / Electrochemical Simulation
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.
New BSD-3-Clause Lithium BatteryElectrochemical ModelDFN

RoseTTAFold: Three-Track Network for Protein Structure and Interaction Prediction

Biomedical / Structure Prediction
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.
New Code is MIT; trained weights and data are under the Rosetta-DL software license for internal, non-commercial research use only Protein Structure PredictionThree-Track NetworkDeep Learning

SU2 Aerodynamic Shape Optimization: Choosing Between Discrete and Continuous Adjoints

Aerospace / Optimization Design
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.
New GNU Lesser General Public License v2.1 Aerodynamic OptimizationAdjoint MethodCFD

Tokamak Plasma Magnetic Confinement Control

Energy / Fusion Control
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.
New Paper copyright retained by the authors; algorithm and libraries under their own open-source licenses FusionReinforcement LearningPlasma Control

TopoDiff: Diffusion-Model Topology Optimization and Its Evaluation Metrics

Structural Optimization / Generative Design / Conditional Diffusion
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.
New CC BY 4.0 for the arXiv version; published at AAAI 2023 Topology OptimizationDiffusion ModelGenerative Design

WEC-Sim Hydrodynamics for Wave Energy Converters in a Physics-AI Workflow

Marine Energy / Multibody Dynamics
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.
New Apache-2.0 (Sandia LLC and NTESS, 2014, with certain rights retained by the U.S. Government under contract DE-NA0003525) Wave EnergyHydrodynamicsMultibody Simulation

Wind Turbine Aeroelastic Simulation and Wake Control: A Verifiable Chain from OpenFAST to Reinforcement Learning

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.
New Apache-2.0 for OpenFAST, FAST.Farm, FLORIS and the IEA Wind Task 55 reference models Wind EnergyAeroelasticityWake Control

Adaptive Physics-informed Neural Networks: A Survey

Survey / Reading Material
A focused survey of PINN improvements via transfer learning and meta-learning, addressing PINN's notorious convergence difficulty and the need to re-optimize on every PDE parameter change - the engineering reference for productionizing PINNs.
arXiv preprint (copyright held by authors) PINNTransfer LearningMeta Learning

CFD Python: 12 Steps to Navier-Stokes

Fluid / CFD / Beginner Tutorial
Lorena Barba classic "12 Steps to Navier-Stokes" - twelve Jupyter notebooks building solvers from 1-D linear convection to 2-D NS and channel flow.
New See LICENSE file CFDFinite DifferenceBeginner

Clawpack Finite-Volume Solvers for Hyperbolic PDEs

Fluid / CFD / Framework Tutorial
LeVeque team finite-volume package - Godunov-type schemes for hyperbolic conservation laws, standard tool for shocks, tsunami, reservoir, and seismic waves.
New BSD-3-Clause Finite VolumeHyperbolic PDEShock Wave

Dedalus Spectral PDE Solver Framework

General SciML / Framework Tutorial
Python framework that builds spectral-method solvers symbolically (Burns et al. 2020), widely used in fluid dynamics, plasma, star and planet research.
New GPL-3.0 Spectral MethodSymbolicPython

DeepXDE Physics-Informed Neural Network Framework

General SciML / Framework Tutorial
The most mature open-source PINN/DeepONet solver framework - one API covering forward, inverse, and multiphysics problems, with Chinese-friendly docs.
New LGPL-2.1 PINNDeepONetFramework

FAIR Chemistry Machine Learning Toolkit

Materials / Chemistry / Framework Tutorial
Meta FAIR Chemistry open-source toolkit (formerly the Open Catalyst Project) spanning OC20/OC22 datasets and models like GemNet, eSCN, EquiformerV2.
New MIT CatalysisMachine Learning PotentialGraph Neural Network

FEniCS Automated Finite Element Platform

Solid / Structure / Framework Tutorial
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.
New LGPL-3.0 Finite ElementFEMVariational Form

FNO (Fourier Neural Operator) Tutorial

Fourier Neural Operator / Beginner Tutorial
Systematic FNO from theory to code - for engineers and researchers wanting neural operators as PDE surrogates.
MIT FNONeural OperatorSurrogate

Finite Element from Scratch in Python

Finite Element / From Scratch
Build a 2D linear-elastic FEM solver from NumPy/SciPy - no FEniCS/Abaqus - to deeply understand every matrix derivation and assembly step.
GPL-3.0 FEMFinite ElementPython

DeepONet Getting Started

Neural Operator / Beginner Tutorial
Systematic DeepONet theory and DeepXDE implementation - for PINN developers handling multiphysics-parameter scenarios.
MIT DeepONetNeural OperatorDeepXDE

Harvard CS249r Machine Learning Systems (Open Textbook, 4 Volumes)

Textbook / Systematic Course
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.
New CC BY-NC-ND 4.0 (book text); CC BY-NC-SA 4.0 (labs/slides) TextbookML SystemsPhysical AI

JAX-CFD Differentiable Computational Fluid Dynamics

Fluid / CFD / Framework Tutorial
Google open-source differentiable CFD codebase - spectral solvers in JAX that let gradients flow through flow-field simulation.
New Apache-2.0 JAXDifferentiable SimulationCFD

A Roadmap for Polymer Informatics Super-Intelligence

Materials
This roadmap reviews the evolution of polymer informatics toward on-demand inverse design, causal reasoning across chemistry, processing, and performance, and closed-loop autonomous experimentation.
See LICENSE file polymer informaticsinverse designautonomous experimentation

Embedding Physics Priors in Robot Learning: A Survey

Multibody
A survey on embedding physics priors in robot learning, covering how physical constraints like contact mechanics, rigid-flexible coupling, and multibody dynamics improve sample efficiency and reliability of learned policies.
See LICENSE file robot learningphysics priorsmultibody dynamics

Optimization with Region-Reduced ReLU Neural Networks

ScientificML
This survey reviews optimization of mathematical models combining integer decisions with ReLU neural networks for chemical and process systems engineering, particularly superstructure optimization using surrogates for complex nonlinear processes.
See LICENSE file ReLU neural networkssurrogate modelschemical process optimization

Quantum Algorithms for Computational Fluid Dynamics

CFD
Reviews quantum approaches for solving partial differential equations in computational fluid dynamics, covering fully quantum and hybrid quantum-classical methods.
See LICENSE file Computational Fluid DynamicsQuantum AlgorithmsPartial Differential Equations

NeuralPDE.jl Scientific Machine Learning Solvers in Julia

General SciML / Framework Tutorial
Julia SciML ecosystem library unifying PINN/DeepONet/NeuralOperator solvers with seamless DifferentialEquations.jl interoperability and GPU/autodiff out of the box.
New MIT JuliaPINNSciML

Operator Learning: A Survey

Survey / Reading Material
A systematic survey of operator learning covering the theory, architectures and error analysis of DeepONet, FNO and their variants - the reference entry point to learning infinite-dimensional maps.
arXiv preprint (copyright held by authors) Operator LearningSurveyDeepONet

PDEBench Scientific Machine Learning Benchmark

General SciML / Benchmark
A unified benchmark (Takamoto et al. 2022) spanning 12+ PDE families that turns "is this operator-learning model good" into comparable numbers.
New See LICENSE file BenchmarkDatasetNeural Operator

PhiFlow Differentiable PDE Solving Framework

Fluid / CFD / Framework Tutorial
TUM differentiable fluid simulation framework - solvers run directly on PyTorch/JAX/TensorFlow tensors with gradients through the solve.
New MIT Differentiable SimulationFluidPyTorch

Physics-Based Deep Learning (Online Book)

Textbook / Systematic Course
A free online textbook from TU Munich covering physics + deep learning: differentiable physics, PINNs, neural operators and turbulence modeling, with runnable code.
CC BY-NC-SA 4.0 TextbookDifferentiable PhysicsPINN

Machine Learning with Physics Knowledge for Prediction: A Survey

Survey / Reading Material
A systematic survey of physics-knowledge + ML methods for PDE prediction, splitting the field into architectural-level (loss, structured prediction, augmentation) and data-level (multi-task, meta, contextual) approaches, with industrial perspective and open-source ecosystem review.
arXiv preprint (copyright held by authors) Physics-informed MLPDEMulti-task Learning

Physics Simulation & ML Integration Roadmap

Learning Roadmap / Systematic Overview
Systematic path from classical PDE numerics to data-driven physics AI - FEM, FVM, surrogates, PINN and their evolution.
CC BY 4.0 RoadmapPDENumerical Method

NVIDIA PhysicsNeMo Physics-AI Framework

General SciML / Industrial Framework
NVIDIA open-source physics-AI training/inference framework (formerly Modulus) with official examples across CFD, structural, EM, weather, and semiconductor TCAD.
New Apache-2.0 PhysicsNeMoModulusIndustrial Deployment

PINN from Scratch

Beginner Tutorial
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.
New MIT PINNTutorialBeginner

pymatgen Materials Genomics Toolkit

Materials / Chemistry / Toolkit Tutorial
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.
New MIT MaterialsCrystal StructurePhase Diagram

PythonRobotics: Python Code Collection and Textbook for Robotics Algorithms

Robotics Algorithms / Learning Codebase
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.
New MIT Robotics AlgorithmsMotion PlanningSLAM

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics

Original Research Paper
ICLR 2026 paper proposing ATOM, a quasi-equivariant pretrained transformer neural operator that requires no explicit molecular graph and uses temporal attention for parallel decoding of multiple future states; curates TG80 (80 compounds, 2.5M fs trajectories) and demonstrates zero-shot generalization on MD17/RMD17/MD22.
arXiv preprint (copyright held by authors) Neural OperatorMolecular DynamicsTransformer

Adaptive Physics Transformer with Fused Global-Local Attention for Subsurface Energy Systems

Original Research Paper
ICML 2026 paper proposing APT, a geometry-/mesh-/physics-agnostic neural operator that fuses graph-based local feature extraction with global attention for long-range physical effects; achieves 4× saturation error reduction on 2D faulted CO2 storage vs prior SOTA, 19,873× speedup over GEOS and 6,800× over ECLIPSE.
arXiv preprint (copyright held by authors) Neural OperatorSubsurface EnergyCO2 Storage

DeepONet (Original Paper)

Foundational Paper
Presents a branch-trunk architecture realizing a deep learning version of the universal operator approximation theorem - the first systematic architecture for learning nonlinear operators and still a mainstream baseline.
arXiv preprint (copyright held by authors) DeepONetNeural OperatorFoundational

Fourier Neural Operator (Original Paper)

Foundational Paper
Introduces neural operators with integral kernels parameterized in Fourier space, enabling resolution-invariant PDE solving - a foundational and highly cited work in physics AI.
arXiv preprint (copyright held by authors) FNONeural OperatorFoundational

Transolver is a Linear Transformer: Revisiting Physics-Attention through the Lens of Linear Attention

Original Research Paper
Reframes Transolver's Physics-Attention as a special case of linear attention and proposes LinearNO (Linear Attention Neural Operator); achieves SOTA on six PDE benchmarks with 40.0% fewer parameters and 36.2% less compute, plus superior performance on AirfRANS and Shape-Net Car industrial datasets.
arXiv preprint (copyright held by authors) Neural OperatorTransformerLinear Attention

Droop-Aware Foundation Model Power Flow

Electromagnetics
Develops a droop-aware extension of GridFM foundation model for power systems, embedding droop gains and deadband parameters as node features for control-aware AC power flow analysis.
See LICENSE file Power SystemsPower FlowFoundation Model

Two-Stage Ordering Kinetics in Binary Mixtures of Ellipsoidal Particles

Materials
Investigating nonequilibrium phase-ordering kinetics in binary mixtures of uniaxial ellipsoidal particles using large-scale molecular dynamics simulations with anisotropic Gay-Berne potential, revealing two-stage ordering processes across different time scales after temperature quench.
See LICENSE file molecular dynamicsphase-ordering kineticsanisotropic potential

Ladder of Information Limits on Prediction for Reduced-Order Models

ScientificML
Proposes a ladder of information limits to quantify predictability boundaries for reduced-order models under limited information, covering memoryless and memory-augmented trajectory forecasts, event prediction, stationary statistics, and generative laws.
See LICENSE file reduced-order modelinformation theoryprediction theory

Quantum-hardware spectral co-design framework for multifrequency Rydberg electrometry

Quantum/Chemistry
A spectral co-design framework that directly couples fabrication-constrained SPSA-Adam optimizer with full-wave finite-element eigenmode simulations for multifrequency Rydberg electrometry, operating without analytical or adjoint gradients.
See LICENSE file quantum hardwarespectral co-designRydberg electrometry

LPINNs: First-Layer Gated Localization for Physics-Informed Neural Networks

ScientificML
LPINNs propose multiplying the first hidden activation of a dense PINN by input-dependent localization functions, endowing first-layer units with receptive fields to improve optimization on long domains and for high-order operators without domain partitioning.
See LICENSE file Physics-Informed Neural NetworksPINN EnhancementNeural Network Localization

Data-Driven MPC with Adaptively Sampled Non-Expert Demonstrations: Performance Guarantees and Sample Complexity

Multibody
This paper proposes a data-driven policy construction method for dynamical systems using non-expert MPC demonstrations, introducing a memory-based nonparametric policy with Lipschitz-regularized upper envelope of the finite-horizon surrogate value function to approximate infinite-horizon optimal control.
See LICENSE file Model Predictive ControlData-Driven ControlReinforcement Learning

Artificial Neural Networks as Surrogate Models in Black Box Optimization

ScientificML
This paper investigates using artificial neural networks as surrogate models for black-box optimization, enabling efficient optimization when analytical function descriptions are unavailable by obtaining objective values through numerical simulation.
See LICENSE file Black-Box OptimizationSurrogate ModelNeural Network

Federating Quantum and Classical Computing: A Privacy-Preserving Hybrid Approach

Quantum/Chemical
This paper presents a privacy-preserving hybrid quantum-classical computing framework that integrates parameterized quantum circuits with classical components, targeting quantum computing proxy applications such as chemistry simulation.
See LICENSE file Quantum Machine LearningHybrid Quantum-Classical ModelsPrivacy-Preserving

Triply-Scalable Equivariant Gaussian Process Modeling

ScientificML
Proposes a triply-scalable equivariant Gaussian process method that encodes symmetries while maintaining probabilistic predictions and uncertainty quantification for large-scale scientific computing.
See LICENSE file Gaussian ProcessEquivariant Neural NetworksUncertainty Quantification

Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks

ScientificML
Proposes a graph hypernetwork approach using an operator graph that explicitly represents PDE fields, derivatives, terms, and residuals as nodes, enabling amortized neural solver meta-training across related partial differential equations.
See LICENSE file Physics-Informed Neural NetworksGraph HypernetworksOperator Graph

Adaptive Minimum-Variance Phase Gradient Estimator Overcomes Trainability Barriers in Neural-Network-Based Variational Quantum Optimization

Quantum/Chemical
For quantum many-body physics and ab initio quantum chemistry, this work derives an unbiased direct gradient estimator and introduces the adaptive minimum-variance phase (AMVP) estimator to overcome training failures in weak-gradient regimes for neural-network variational optimization.
See LICENSE file Quantum Many-Body PhysicsVariational OptimizationGradient Estimation

K-TRAIL: Simulator-Guided Generative Design of EM/RF Circuits

Electromagnetics
K-TRAIL is a simulator-guided generative framework combining diffusion-based layout generation with derivative-free ensemble Kalman guidance for automated EM/RF circuit inverse design.
See LICENSE file EM inverse designRF circuitsdiffusion model

Complete Neural Electronic Initialization Accelerates Materials DFT

Materials
Presents the first complete machine learning method for accelerating plane-wave DFT in materials under the PAW formalism, formalizing seven criteria that a Complete Neural Electronic Initializer must satisfy and addressing two missing structure-dependent components: augmentation occupancies and spin initialization.
See LICENSE file Density Functional TheoryMachine LearningMaterials Science

GPCR Ligand Bioactivity Prediction with Physics-Informed Dual-State Query Learning

Quantum/Chemistry
A physics-informed dual-state query learning framework for GPCR ligand bioactivity prediction, addressing the neglect of dynamic conformational equilibria in existing deep learning approaches to improve functional efficacy discrimination.
See LICENSE file GPCR ligandbioactivity predictionphysics-informed learning

Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients

Geophysics
This paper presents a domain-decomposed random-feature evolutional deep neural network (DD RF-EDNN) for solving transient pressure diffusion in heterogeneous porous media with discontinuous and high-contrast permeability, combining spatial approximation with temporal evolution.
See LICENSE file porous mediapressure diffusiondomain decomposition

Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery

ScientificML
Proposes Graph Wavelet Compressed Sensing (GWCS) for offline compression of graph signals via sparse wavelet-domain representations, reducing data preparation costs for scientific machine learning training.
See LICENSE file graph signal processingwavelet transformcompressed sensing

Emulation strategies for Bayesian inference of regional left ventricle material parameters

Biomechanics / Computational Medicine
This paper introduces a Bayesian surrogate-modeling framework for inferring regional Holzapfel-Ogden material parameters in a left ventricle partitioned into five physiological zones, using cardiac MRI data to overcome the limitation of treating the myocardium as mechanically homogeneous.
See LICENSE file Cardiac BiomechanicsBayesian InferenceSurrogate Modeling

Fast Surrogate for the Earth Matter Effect on Solar Neutrinos

ScientificML
A deep-learning surrogate model based on residual CNN predicts Earth-induced transition probabilities for solar neutrinos across energy and zenith angle parameter space.
See LICENSE file neutrino oscillationEarth matter effectdeep learning surrogate

Riemannian Simultaneous Inference for Tangent Vector Field Regression

ScientificML
Proposes a kernel estimator for nonparametric tangent vector field regression on Riemannian manifolds without boundary, using parallel transport and volume correction, with theoretical derivation of uniform second-order bias and stochastic convergence rates.
See LICENSE file Riemannian geometrytangent vector fieldnonparametric estimation

Backward log orthogonal functions and their approximation theory

ScientificML
Introduces backward logarithmic orthogonal functions constructed via terminal-endpoint logarithmic mapping of generalized Laguerre polynomials, designed for backward spectral approximation of problems with weak endpoint singularities.
See LICENSE file spectral methodsorthogonal functionsapproximation theory

Enhancing Transformer Representations of Symbolic ODE Expressions

ScientificML
Proposes Transformer-based learning of structured representations for symbolic ODE expressions, preserving commutative properties to enable mathematical reasoning in symbolic form, distinct from traditional methods relying on numerical fitting.
See LICENSE file Symbolic ComputationODETransformer

Continental-scale probabilistic resistivity imaging of Australia using deep learning: Implications for geology, groundwater, and critical minerals

Geophysics
A continental-scale electrical resistivity model of Australia's shallow crust (up to ~650 m depth) derived from probabilistic deep learning inversion of 26.6+ million AEM soundings, with quantified uncertainty for geology, groundwater, and critical mineral exploration.
See LICENSE file Airborne EMResistivity imagingProbabilistic inversion

Scalable Incremental Robustness Analysis of Neural Network Feedback Systems

ScientificML
Proposes a unified scalable framework combining structured decomposition with SDP certificates and small-gain analysis for robust stability and performance analysis of feedback systems with high-dimensional NNs and unmodeled dynamics.
See LICENSE file neural network verificationrobust controlsemidefinite programming

Geometry-Aware Anisotropic Boundary Correction for Aerodynamic Simulation

CFD
Proposes a geometry-aware anisotropic boundary correction method using neural operators as an efficient alternative to traditional CFD solvers for aerodynamic simulation, improving physical modeling near solid boundaries.
See LICENSE file aerodynamicsboundary correctionneural operator

Physics-informed generative AI for semiconductor manufacturing: Enforcing hard physical constraints in generative models by construction

ScientificML
Proposes a method to enforce hard physical constraints in generative models for semiconductor manufacturing by construction, ensuring that generated masks, layouts, and process recipes strictly comply with lithography, transport, reaction, and device-physics constraints.
See LICENSE file semiconductor manufacturingphysics-informed learninggenerative AI

Towards Physics-Informed Neural Networks for Stiff Guitar String Vibrations

Structural
Investigates the effectiveness of Physics-Informed Neural Networks in simulating transverse vibration of one-dimensional linear stiff strings by incorporating PDE constraints and boundary conditions into the loss function.
See LICENSE file Physics-Informed Neural Networksstiff string vibrationsolid mechanics

MIISO: Modal Integrators for Isogeometric Stabilization of Outliers

Structural
A modal integrator framework (MIISO) is proposed to stabilize non-physical outlier modes at the top of the discrete spectrum in high-order isogeometric discretizations, improving numerical solutions in wave propagation and structural dynamics.
See LICENSE file isogeometric analysisstructural dynamicswave propagation

SPUS PDE-UNet-36M-v2 (FNS-KF) PDE Solving Model

ScientificML
A 36M-parameter UNet-based PDE solver v2 by Los Alamos National Laboratory, designed for surrogate modeling of partial differential equations in scientific computing.
See LICENSE file PDE SolvingUNetNeural Operator

Fourier Neural Operators for Rayleigh-Bénard Convection

CFD
Proposes an improved Fourier Neural Operator for modeling 2D Rayleigh-Bénard convection by predicting time increments, achieving a compact model (314k parameters, 7ms inference) while revealing accuracy limitations imposed by training data resolution.
See LICENSE file Fourier Neural OperatorRayleigh-Bénard ConvectionFluid Mechanics

A Contrast-Source Inversion Scheme Based on Stochastic Optimization and Plug-and-Play Regularization

Electromagnetics
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 file electromagnetic inversioncontrast-source inversionstochastic optimization

A Monolithic Discontinuous Galerkin Framework for Darcy Optimal Control with Radon-Measure Tracking and Pointwise Control Constraints

CFD
A monolithic discontinuous Galerkin discretization for an elliptic optimal control problem governed by Darcy's equation in heterogeneous porous media, tracking pressure states on points, curves, and subdomains through a single Radon-measure formulation with pointwise box constraints on the control.
See LICENSE file Darcy flowDiscontinuous GalerkinOptimal control

A Parallel Solver for Vortex-Induced Vibrations at Zero Mass Ratio

CFD
The paper presents a parallel monolithic finite element strategy for simulating two- and three-dimensional vortex-induced vibrations of a rigid, massless cylinder mounted on translational springs.
See LICENSE file vortex-induced vibrationscylinder flowparallel solver

A Systematic Comparison of Hard- and Soft-Constrained Physics-Informed Molecular Machine Learning with the Clapeyron Equation

Materials
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 file Physics-informed molecular MLClapeyron equationThermodynamic constraints

A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges

Structural
A scalable bridge digital-twin framework combines vehicle–bridge interaction modelling, vibration measurements, state estimation, machine learning, and surrogate modelling for structural condition assessment.
See LICENSE file bridge digital twinvehicle–bridge interactionstructural condition assessment

NeuIDO: Neural Intrinsic Dynamics Operator for Physics-Informed 4D World Models

ScientificML
NeuIDO proposes a neural intrinsic dynamics operator that internalizes physical constraints into world models for predicting 3D object interaction trajectories, bridging the gap between physics-informed 4D generation and true world models.
See LICENSE file World ModelPhysics-Informed GenerationNeural Operator

Expanding RCWA Capabilities with Advanced S-matrix Algorithms

Electromagnetics
Introduces a reformulation of the S-matrix approach for layered photonic structures, defining the S-matrix as an intrinsic layer property independent of neighboring interfaces to enhance numerical stability.
See LICENSE file RCWAS-matrixphotonic structures

Neural Modal Decomposition: Architectural Priors from Observables

Electromagnetics
Proposes Neural Modal Decomposition (NMD) to decompose multi-port system response matrices into pole-residue form for neural network-based modeling of RF cavities and photonic devices.
See LICENSE file Neural Modal DecompositionElectromagnetic ModelingMulti-port System

Active Self-Consistent Field Theory for Ornstein-Uhlenbeck Polymers

Materials / Soft Matter
Proposes active self-consistent field theory (ASCFT) for studying steady-state behavior of active Ornstein-Uhlenbeck polymers, extending classical polymer field theory to non-equilibrium systems.
See LICENSE file Active PolymersSelf-Consistent Field TheoryNon-Equilibrium Statistical Mechanics

Adaptive Interaction Graphs for Particle Simulation

ScientificML
This paper addresses graph neural network-based particle simulation by making interaction graphs adaptive to local model confidence. The proposed approach trains per-particle variance and acceleration heads jointly, aiming to improve long-horizon predictions where errors otherwise compound.
See LICENSE file Particle SimulationGraph Neural NetworksAdaptive Interaction Graphs

Architecture Acceleration of Machine Learning Gravitational Waveform Surrogate Models

Geophysics
This paper presents differentiable and hardware-accelerated implementations of the machine-learning surrogate models mlgw and mlgw-bns for gravitational-wave waveform modeling, enabling JIT compilation, vector parallelization, GPU acceleration, and automatic differentiation within JAX.
See LICENSE file gravitational waveswaveform surrogate modelsGPU acceleration

Beyond Point Prediction: Artificial Representative Trees with Uncertainty

ScientificML
Proposes combining Artificial Representative Trees with leaf-wise Mondrian Conformal Predictive Systems to enable a single decision tree to provide continuous predictions, prediction intervals, and probabilistic outputs as an interpretable ML approach.
See LICENSE file Decision TreesInterpretable MLUncertainty Quantification

Acoustic Dip in the Effective Temperature of Hot Brownian Motion

Acoustics
This paper investigates the acoustic dip phenomenon in the effective temperature of hot Brownian particles in compressible solvents, revealing how finite sound speed modifies the fluctuation-dissipation relation in the kinetic regime.
See LICENSE file hot Brownian motionacoustic effectfluctuation-dissipation

How Much Memory Do We Need? Adaptive Memory Gate for Neural Operators

ScientificML
Proposes an adaptive memory gating mechanism enabling neural operators to dynamically adjust memory weights based on observation conditions, improving adaptability in solving time-dependent PDEs.
See LICENSE file Neural OperatorsAdaptive MemoryTime-dependent PDE

An improved periodic activation for PINNs reconstructing convective flows

ScientificML
This paper proposes an improved periodic activation using complex exponential functions generating paired sine-cosine outputs for Physics-Informed Neural Networks, demonstrating superior performance over sine-activated MLPs in reconstructing temperature fields from sparse velocity data in convective flows.
See LICENSE file PINNsperiodic activationconvective flows

TASE-Stabilized Time-Evolving Natural Gradient Methods for Diffusion-Dominated PDEs

ScientificML
Proposes TASE-stabilized Time-Evolving Natural Gradient (TENG) method that projects time-discrete target states onto the neural-network manifold via local natural-gradient iterations to address stability constraints in stiff diffusion-dominated PDEs.
See LICENSE file Time-Evolving Natural GradientDiffusion-Dominated PDEsNeural PDE Approximation

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

ScientificML
Proposes a nearly-instant latent space Bayesian optimization method that replaces expensive sequential decision-making with sampling overhead, making BO practical for generative model-driven de novo design pipelines with cheap virtual screens.
See LICENSE file Bayesian OptimizationLatent Space OptimizationGenerative Design

A Variational Optimal Transport Operator on Incompressible Flow

CFD/Fluid Dynamics
VIOT is a generative neural operator for incompressible density transport that predicts divergence-free velocity fields via feed-forward inference, replacing hour-scale optimization in adjoint fluid solvers and enabling rapid transport trajectory generation.
See LICENSE file Incompressible FlowNeural OperatorOptimal Transport

Integral Chemical Reaction Neural Networks

Quantum/Chemical
Proposes iCRNNs to discover chemical reaction network structures and kinetics from time-series concentration data without prior mechanistic assumptions, balancing interpretability and computational efficiency.
See LICENSE file Chemical Reaction NetworksNeural NetworksChemical Kinetics

NeSTR: Neural S-Transform Reconstruction for Gaussian SPDEs

ScientificML
Proposes NeSTR method that learns the S-Transform on a finite dimensional subspace of white noise test space to reconstruct stochastic solutions for Gaussian SPDEs.
See LICENSE file SPDENeural S-TransformGaussian Process

CANTO: CAD-Native Transformer Operators for AI-Aided Engineering

ScientificML
CANTO presents CAD-native transformer operators for engineering numerical simulation, targeting the computational and representation burden caused by meshing continuous parametric geometry.
See LICENSE file CAD-native operatorsTransformer operatorsengineering simulation

LOInK: Learned Optimal Inverse Kinematics via Structured Neural Surrogate Models

Multibody
LOInK learns a bi-Lipschitz invertible mapping from configuration space to a decoupled task/latent space, structuring the latent space so that cost-minimizing solutions are placed at the origin, enabling efficient sampling of approximately optimal inverse kinematics solutions.
See LICENSE file Inverse KinematicsNeural Surrogate ModelRobotics

CFD-Machine Learning Driven Pod Optimization and Staged Pressure-Area Management for Supersonic Evacuated Tube Transport

CFD
This paper presents an integrated CFD-machine learning framework for optimizing pod geometry in supersonic evacuated tube transport, using composite cubic Bezier curves with seven design variables and Latin Hypercube Sampling to evaluate 200 configurations across subsonic and supersonic regimes.
See LICENSE file evacuated tube transportsupersonic aerodynamicspod optimization

Charge Regulation Mediated Interaction of Amphoteric Nanoparticle Surfaces

Materials
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 file amphoteric nanoparticlescharge regulationmolecular dynamics

CI-PINN: Causal Integral Physics-Informed Neural Network for Solving Evolution Equations

ScientificML
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 file evolution equationsphysics-informed neural networkscausal integral network

Cluster Attention Neural Operators for Solving Parametric Partial Differential Equations

ScientificML
This paper presents cluster attention neural operators for solving parametric partial differential equations. It targets physical-field simulation by learning solution operators to accelerate parameter-space mapping, while addressing the quadratic attention complexity associated with Transformer-based neural operators.
See LICENSE file neural operatorsparametric PDEscluster attention

Combining physical models with dynamically acquired experimental information for the optimization of multicomponent NASICON fast ionic conductors in a self-driving laboratory

Materials
A self-driving laboratory strategy that simultaneously and dynamically assesses composition-dependent synthetic accessibility and target properties via aggregated cost functions to accelerate optimization of multicomponent NASICON fast ionic conductors while maintaining phase purity.
See LICENSE file NASICONfast ionic conductorself-driving laboratory

Continuous-Time Trajectory Generation from Discrete Observations with Stochasticity

ScientificML
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 file continuous-time trajectory generationdiscrete observationsstochastic physical systems

CP-Agent: A Harness-Engineered Agent for Crystal Plasticity Simulation Workflows

Materials
CP-Agent is an agentic harness for crystal plasticity simulation workflows in polycrystalline metals, automating heterogeneous tool configuration, multi-step data pipeline orchestration, and constitutive parameter calibration against experiments.
See LICENSE file crystal plasticitypolycrystalline metalssimulation workflow

Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems

ScientificML
This paper develops Physics-Informed Neural Networks and Deep Operator Networks for infinity and p-Laplace problems, targeting nonlinear PDE solvers across 2D and 3D domains with p values from 2 to 1000.
See LICENSE file Physics-Informed Neural NetworksDeep Operator NetworksNonlinear Partial Differential Equations

Differentiable Dynamics for Autonomous Micro-Mobility Navigation

Multibody
This paper presents differentiable dynamics for autonomous micro-mobility vehicles, modeling tire slip, friction, and wheel layouts to improve realistic and predictable low-speed navigation in pedestrian-shared spaces.
See LICENSE file differentiable dynamicsmicro-mobility navigationvehicle motion modeling

Discrete Quality-Factor Control in a Side-Coupled Photonic Crystal Microcavity: Evanescent Bloch Tunnelling and the Finite-Cell Correction

Electromagnetics
This paper studies electromagnetic control of resonance and quality factor in a side-coupled microcavity made from a two-dimensional photonic crystal of silicon rods in an aqueous analyte. It uses plane-wave expansion and finite-difference time-domain computation to examine evanescent Bloch tunnelling and finite-cell corrections.
See LICENSE file photonic crystal microcavityelectromagnetic simulationquality-factor control

Distance-Residual Physics-Informed Neural Networks: A Deep Learning Framework for Differential and Partial Differential Inclusions

ScientificML
Distance-Residual Physics-Informed Neural Networks provide a physics-informed deep learning framework for ordinary and partial differential inclusions. The method uses the squared distance from a differential operator to an admissible set-valued map instead of the classical pointwise PDE or ODE residual.
See LICENSE file Physics-Informed Neural NetworksDifferential InclusionsScientific Machine Learning

DNNsolver: Accurate and Efficient Deep Learning Modeling of Polarization-Sensitive Diffractive Neural Networks

Electromagnetics
DNNsolver introduces a deep learning-based approach for modeling polarization-sensitive diffractive neural networks, addressing the limitation of thin element approximation in capturing intra-layer electromagnetic coupling for improved accuracy and efficiency in high-density optical computing.
See LICENSE file Diffractive Neural NetworksPolarization-SensitiveElectromagnetic Coupling

Does Transolver Really Need a Transformer?

CFD
This paper provides an empirical and theoretical analysis of Transolver’s physics-attention mechanism for three-dimensional fluid dynamics, examining how unstructured mesh points are assigned to slices, tokens interact through self-attention, and results are broadcast back to the points.
See LICENSE file neural operatorsphysics-attentionfluid dynamics

Doubly exponential convergence of the cyclic steepest descent method for strictly convex quadratics in arbitrary dimensions

ScientificML
This paper studies the convergence properties of the cyclic steepest descent (CSD) method for minimizing strictly convex quadratic functions in arbitrary dimensions, proving doubly exponential convergence rates and extending prior theoretical results limited to two-dimensional cases.
See LICENSE file numerical optimizationconvex optimizationcyclic steepest descent

Dynamical Diversity for Reservoir Computing in Reconfigurable Nanomechanics

Structural
This nanomechanics study demonstrates physical reservoir computing with two interacting modes of a single nanoelectromechanical resonator, using geometric Duffing nonlinearity, fading memory, and one readout port.
See LICENSE file nanoelectromechanical systemsreservoir computingnonlinear dynamics

Beyond Phase Reduction: Amplitude Collapse in Optimal Control of Coupled Oscillators

Multibody
This paper solves the four-dimensional HJB equation for two diffusively coupled Stuart-Landau-like oscillators to obtain full-state optimal feedback control, revealing a sharp transition in control strategy from phase synchronization to amplitude collapse at a critical coupling threshold.
See LICENSE file coupled oscillatorsHJB equationamplitude collapse

The Scott-Vogelius Element is Inf-Sup Stable on Freudenthal Meshes for k ≥ 4

Structural
This paper rigorously establishes inf-sup stability of the Scott-Vogelius finite element on three-dimensional Freudenthal meshes for polynomial degree k ≥ 4, completing the theoretical framework for this classical divergence-free mixed element used in Stokes flow computations.
See LICENSE file finite element methodsStokes probleminf-sup stability

GENERIC-FNO: Embedding Energy Conservation and Entropy Production into Fourier Neural Operators

ScientificML
GENERIC-FNO embeds the metriplectic degeneracy structure of nonequilibrium thermodynamics into Fourier neural operators, coupling reversible energy-conserving and irreversible entropy-producing dynamics via degeneracy conditions, extending structure-preserving neural operators beyond single conservation laws.
See LICENSE file neural operatorFourier neural operatorthermodynamics

Predictive Uncertainty for Neural CAE Surrogates

ScientificML
Investigates how uncertainty quantification approaches perform when adapted to geometry-conditioned neural surrogates for CAE, comparing closed-form and sampling-based methods across varying geometries and engineering quantities of interest.
See LICENSE file neural surrogatesuncertainty quantificationCAE simulation

Energetically Driven Structure Matching for Autonomous Total X-ray Scattering Experiments

Materials
This materials-science study presents an energetically driven structure-matching framework for analyzing ongoing total X-ray scattering experiments, using gold nanoparticle data to compare idealized spherical, octahedral, decahedral, and icosahedral structures.
See LICENSE file Total X-ray scatteringNanoparticle structureAutonomous laboratories

Energy-Efficient Operation of Neural Operators for Virtual Sensing

Thermal Management
This paper investigates shared spatial computation for energy-efficient neural-operator virtual sensing. It evaluates operating-energy reductions in a heat-exchanger service while retaining the selected checkpoint and its evaluated predictions.
See LICENSE file Neural OperatorsVirtual SensingEnergy-Efficient Computing

Enhancing Generalization in Endwall Film Cooling Prediction: Incorporating the Superposition Principle into Transformer-Based Neural Operators

CFD
This paper proposes a physics-enhanced neural operator for turbine endwall film cooling by incorporating the superposition principle into a transformer-based model. The approach targets temperature-field prediction across cooling layouts with varying numbers of film holes, focusing on improved generalization in fluid cooling analysis.
See LICENSE file Film CoolingNeural OperatorTransformer

Equation Discovery with Bayesian Tree-Adjoining Grammars

ScientificML
A Bayesian tree-adjoining grammar framework for equation discovery and structure identification in general nonlinear systems.
See LICENSE file equation discoveryBayesian modelingtree-adjoining grammars

Exact Equivariance from Ordinary Neural Networks for Lattice Many-Body Dynamics

Quantum/Chemistry
Proposes using ordinary multilayer perceptrons with finite-group averaging to achieve exact equivariant surrogate models for correlated electron systems, enabling efficient force and transition energy evaluations.
See LICENSE file Quantum Many-BodyEquivariant Neural NetworksElectronic Structure

MARC-TS: Learning Continuous Reaction Paths for Transition-State Prediction

Quantum/Chemical
MARC-TS introduces a two-stage framework that learns endpoint-conditioned continuous reaction paths, queries at arbitrary resolution, and refines transition-state candidates via local path context, with T1x-IRC-8K dataset of 8,209 reactions and 1.09M path-resolved geometries.
See LICENSE file reaction pathtransition statechemical reaction

LiNiO2/NiO Phase Prediction Using Artificial Neural Networks

Materials
Neural networks trained on 4DSTEM diffraction patterns enable rapid identification of LiNiO2 and NiO material phases, providing a computationally efficient approach for analyzing large sets of materials image data.
See LICENSE file Phase Prediction4DSTEM DiffractionNeural Networks

CHOREO: Every Humanoid Skill as a Trajectory

Multibody
CHOREO enables training-free composition of heterogeneous humanoid skills learned via reinforcement learning, motion imitation, and generative modeling, bridging incompatible representations, interfaces, and controllers through unified trajectories.
See LICENSE file humanoid roboticsskill compositiontrajectory representation

AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training

ScientificML
Proposes Adaptive Operator Transformation (AOT) to address structural diversity challenges in multi-PDE pre-training by adapting target solution operators rather than increasing model capacity, improving neural operator generalization across equations.
See LICENSE file Neural OperatorPDE Pre-trainingAdaptive Transformation

Fourier-Geometric Circuit Design for Gate and Entanglement Placement in Quantum Neural Networks

Quantum
This paper expresses the output of a parameterized quantum circuit as a finite Fourier series and uses Fourier-geometric metrics to analyze how the arrangement of trainable and entangling gates shapes the Fourier coefficients, turning prior analysis into explicit design criteria for gate and entanglement placement in quantum neural networks.
See LICENSE file quantum machine learningquantum circuitFourier analysis

Fourier Symmetrization for Geometric Quantum Machine Learning

Quantum
This quantum machine learning paper studies how Fourier symmetrization shapes model expressivity and guides the design of geometric quantum models.
See LICENSE file geometric quantum machine learningFourier symmetrizationquantum models

FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation

Structural
FracGen generates controllable fracture dynamics from a single image of an intact object using fracture-related physical signals. Its training data comes from FracSim, a fracture simulation framework combining material point dynamics with a continuum damage model.
See LICENSE file fracture mechanicsphysics-informed generationmaterial failure simulation

Freezing Calderón: Robust Preconditioning for Maxwell Scattering under Shape Uncertainty

Electromagnetics
This paper studies robust preconditioning for boundary-element discretizations of the Maxwell electric field integral equation under shape uncertainty, with a preconditioner assembled once at nominal geometry and reused across connectivity-preserving perturbations.
See LICENSE file Maxwell scatteringCalderón preconditioningShape uncertainty

Function-Space Transformer with Adaptive Anchors

ScientificML
A function-space Transformer with adaptive anchors targets continuous-domain physical fields, addressing the trade-off between resolving localized variation and computation over fixed uniform grids. The abstract relates this approach to neural operators and latent-attention architectures.
See LICENSE file physical fieldsneural operatorscontinuous-domain modeling

Gnomon: Physics-Informed Link-State Forecasting for LEO Networks

Electromagnetics
Gnomon introduces a physics-informed system that reconstructs LEO satellite serving geometry and signal attenuation to forecast user-perceived downlink/uplink throughput and RTT under varying trace availability.
See LICENSE file LEO satellitePhysics-Informed Neural Networklink prediction

Gradient Surgery for Physics-Informed Neural Networks

ScientificML
This paper studies gradient conflicts and multi-task optimization in Physics-Informed Neural Networks, with implications for more stable convergence in stiff and high-frequency partial differential equations.
See LICENSE file Physics-Informed Neural NetworksGradient ConflictsMulti-Task Optimization

Gravity-Informed Neural Networks for Post-Newtonian Binary Dynamics

ScientificML
GravINNs embeds post-Newtonian equations of motion directly into neural network training to learn binary orbital dynamics, including single-orbit surrogates and extensions across a four-dimensional parameter space.
See LICENSE file gravity-informed neural networkspost-Newtonian approximationbinary dynamics

GridSFM: A Foundation Model for Solving AC Optimal Power Flow

Power Systems
A physics-informed GNN-based foundation model for AC-OPF, pretrained across 54 grid topologies (500-4,000 buses), achieving 2.45% zero-shot generation-cost error on 10,000-bus systems.
See LICENSE file AC-OPFGraph Neural NetworkPower System Optimization

Hydrogen-Stabilized Multimodal High-Index Twin Network in Iron

Materials
This materials-science study examines how hydrogen affects phase transformation and deformation twinning in body-centered-cubic iron using a density-functional-theory-trained deep-neural-network interatomic potential and large-scale molecular dynamics. It reports that hydrogen lowers the yield stress.
See LICENSE file hydrogen effectsdeformation twinningplasticity of iron

Improving Function Space Flow Matching with Kernel Optimal Transport

ScientificML
The paper develops function-space generative modeling for PDE solutions and other function-valued data, using kernel optimal transport to improve the endpoint pairing inherited by Functional Flow Matching.
See LICENSE file Function-space generative modelsFlow matchingPDE solutions

Inference of Hamiltonian and Lie-Poisson Structures from Vector Field Samples

ScientificML
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 file Hamiltonian dynamicsLie-Poisson structuresvector-field inference

Into the Danger Zone: Stable Extrapolation in High-Dimensional Function and Operator Learning

ScientificML
This paper studies out-of-distribution regression in scientific machine learning, focusing on conditions for stable extrapolation in high-dimensional function and operator learning. It analyzes how assumptions on target functions or operators affect extrapolation beyond the training domain and reviews existing bounds based on distribution-discrepancy penalties.
See LICENSE file scientific machine learningout-of-distribution generalizationoperator learning

Isotonic Surrogate Modeling for Computer Experiments with Many Input Variables

ScientificML
This paper develops isotonic Bayesian surrogate modeling for computer experiments involving many input variables and complex physical phenomena, including particle collisions and rocket propulsion. The method incorporates monotonicity or isotonicity information elicited from physical systems to improve surrogate modeling when the available sample size is limited, while retaining uncertainty quantification.
See LICENSE file Bayesian surrogate modelingIsotonic modelingMonotonicity constraints

JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation

Multibody
JAMB proposes jointly denoising bimanual actions and motion states, explicitly modeling geometric interactions between arms in shared 3D scenes to enable coordinated manipulation.
See LICENSE file bimanual manipulationdiffusion policyaction generation

KernelOnet: An Interpretable Neural Operator Based on Kernel Functions

ScientificML
KernelOnet is an interpretable neural operator framework that incorporates kernel functions explicitly into its architecture, aligning the operator structure with boundary-type kernel-expansion forms for physics modeling.
See LICENSE file neural operatorskernel functionsinterpretable machine learning

Kolmogorov-Arnold Networks for Free-Boundary Partial Differential Equations

ScientificML
This paper develops a physics-informed Kolmogorov-Arnold Network framework for free-boundary PDEs, incorporating obstacle constraints, PDE inequalities, complementarity conditions, and boundary conditions into residual-based losses for elliptic and phase-change problems.
See LICENSE file free-boundary problemsphysics-informed learningKolmogorov-Arnold Networks

Lagrangian and Hamiltonian Neural Networks With a Dissipative System

Multibody
This paper investigates Lagrangian and Hamiltonian neural network models for dissipative mechanical systems with explicit time dependence, using damped and undamped one-dimensional harmonic oscillators as simulated systems.
See LICENSE file Lagrangian Neural NetworksHamiltonian Neural NetworksDissipative Systems

Latent Score-Based Bayesian Cramér-Rao Bound Estimation for High-Dimensional Imaging Systems

ScientificML
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 file Bayesian Cramér-Rao BoundHigh-Dimensional ImagingImaging Inverse Problems

Latent Twin Operator

ScientificML
Latent Twin Operator is a latent-space surrogate for time-evolving PDEs that uses a ConvCNP-style encoder and decoder to process sensor observations at arbitrary placements and support queries at any resolution.
See LICENSE file latent-space surrogatetime-evolving PDEsconditional neural process

Learning-Based Pressure Predictive Control of a Vertebraic Soft Robotic Tail

Multibody/Robotics
This paper presents an LSTM-based pressure predictive control method for motion control of a vertebraic soft robotic tail. The approach targets nonlinear material behavior and complex continuum kinematics, and coordinates the tail with a quadruped robot.
See LICENSE file soft roboticspressure predictive controlLSTM

Learning Operators of Geometry with an Interface Autoencoder

ScientificML
Proposes Interface Autoencoder (IAE) for learning neural operators on geometry-dependent PDEs, representing interface-function states in a fixed domain via finite projection codes.
See LICENSE file Neural OperatorsPDEInterface Autoencoder

Material and Thermal Properties of MgCl2 Molten Salt by Ab Initio and Machine-Learning Molecular-Dynamics Simulations

Materials
This paper studies the structural, thermophysical, and dynamical properties of MgCl2 molten salt over a wide temperature range using AIMD and molecular dynamics simulations driven by machine-learning interaction potentials. The MLIP approach is reported to achieve near-AIMD accuracy at a fraction of the computational cost, enabling larger systems and longer timescales.
See LICENSE file MgCl2 molten saltMolecular dynamicsMachine-learning interaction potentials

Mechanism-Resolved Phase-Field Fracture of Composite Shells with a Certified Admissible Constitutive Operator

Structural
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 file phase-field fracturecomposite shellsconstitutive modeling

MENO: Memory-Efficient Neural Operator

ScientificML
A high-performance PDE neural solver based on Manifold Function Encoder, featuring resolution-independent memory footprint and arbitrary PDE input support for large-scale physical simulations.
See LICENSE file Neural OperatorPDE SolverMemory Efficiency

Modelling Non-Linear Aeroelastic Loads in Long-Span Bridges with Extreme Learning Machines

Structural
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 file aeroelasticitylong-span bridgesextreme learning machines

Neural Harmonic Measure Operator

ScientificML
NHMO is a neural solver for elliptic PDEs on variable-shape domains that learns harmonic measure using a transformer-based boundary kernel supervised by Walk-on-Spheres exit samples.
See LICENSE file Elliptic PDEHarmonic MeasureTransformer Boundary Kernel

NEXT: Physics-Informed Neuro-Spectral Exponential Time Differencing Architectures

ScientificML
NEXT presents physics-informed neuro-spectral exponential time-differencing architectures for time-dependent PDEs, targeting the spectral bias and causality limitations of PINNs and the numerical instability of NeuSA for stiff differential equations in neural representations.
See LICENSE file physics-informed neural networksneuro-spectral architecturesexponential time differencing

Nonlinear Excitation of Ideal Anapoles

Electromagnetics
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 file Optical anapolesNonlinear opticsNanoelectromagnetics

On the Limits of Univariate Deep Learning for Significant Wave Height Forecasting

Fluid Mechanics
This study evaluates five deep learning architectures for univariate significant wave height forecasting using buoy observations. Across a 47-buoy, 37-year evaluation corpus, the model families converge to nearly identical performance, with an between-family standard deviation of 0.0014 square meters.
See LICENSE file significant wave height forecastingocean buoysdeep learning comparison

One-Step Generative Surrogate Models via Block-Triangular Joint Drifting

ScientificML
Proposes block-triangular joint drifting to overcome the challenge of estimating conditional distributions in stochastic transition modeling, enabling one-step generative surrogate models for trajectory data prediction.
See LICENSE file generative surrogate modelstochastic processstate transition

Optimal Bias Potentials via Ergodic Optimal Control and Generator Learning

Materials
This paper formulates optimal biasing as an ergodic optimal control problem, recast as a linear eigenvalue problem for the infinitesimal generator of unbiased dynamics to learn bias potentials that accelerate transitions between metastable states in molecular dynamics.
See LICENSE file molecular dynamicsoptimal controlgenerator learning

PGDM-MRSRGAN: Physics-Guided Degradation Model with an SRGAN Framework for Magnetic Resonance Image Super-Resolution

ScientificML
The paper develops a physics-guided degradation model (PGDM) and a super-resolution GAN framework (MRSRGAN) to improve reconstruction of low-field MRI images suffering from low signal-to-noise ratio and limited spatial resolution, targeting biomedical medical imaging inverse problems.
See LICENSE file MRI super-resolutionphysics-guided degradationsuper-resolution GAN

PHASE: Multi-Regime Modeling of Incompressible Magnetohydrodynamics

ScientificML
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 file magnetohydrodynamicssurrogate modelingmulti-regime modeling

Physics-Aware Machine Unlearning for Cyber-Physical Systems

Scientific ML
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 file Machine UnlearningPhysics-Guided LearningCyber-Physical Systems

Physics-Informed Learning of Feedback-Linearizing Representations

ScientificML
The paper proposes a cascaded physics-informed neural network (PINN) framework that numerically solves the PDEs governing feedback-linearizing coordinate transforms, whose well-posedness follows from the Lie-algebraic Frobenius theorem, making them tractable for large-dimensional nonlinear control systems.
See LICENSE file Physics-Informed Neural NetworkFeedback LinearizationNonlinear Control

Physics-Informed Neural Networks for Depth-Averaged Avalanche Dynamics

Geophysics
This study develops a PINN framework for the Savage-Hutter model of depth-averaged granular flow to support mountain avalanche hazard assessment. It advances from one-dimensional analytical verification of three problems to two-dimensional experimental validation of avalanche dynamics.
See LICENSE file physics-informed neural networksavalanche dynamicsdepth-averaged granular flow

Physics-Informed Neural Operator Surrogate for 2D Magnetohydrodynamic Reconnection

Electromagnetics
A physics-informed neural operator learns the map between function spaces in magnetohydrodynamic simulations, enabling efficient state inference for magnetic reconnection at any parameter and time step, significantly reducing computational cost at high Lundquist numbers.
See LICENSE file MagnetohydrodynamicsMagnetic ReconnectionNeural Operator

Physics-Informed Self-Supervised Generation of Digital Brain MRI Phantoms from Weighted Images Using Differentiable MRI Simulation

Scientific ML
This work develops a physics-informed, self-supervised framework for generating digital brain MRI phantoms from conventional weighted MR images without ground-truth parametric maps or anatomical segmentation. It predicts T1, T2, and proton-density maps and reconstructs the input images through a differentiable MRI signal model.
See LICENSE file Digital Brain MRI PhantomsPhysics-Informed Machine LearningSelf-Supervised Learning

Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters

High-Energy Physics
A physics-informed self-supervised learning framework that jointly performs wire calibration and interaction position reconstruction in multi-wire parallel plate avalanche counters, enhancing adaptability to changing operating conditions and detector aging.
See LICENSE file particle detectorwire calibrationposition reconstruction

Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs

Geophysics
This work addresses spatiotemporal forecasting on open-boundary hydrologic graphs, where external forcing such as upstream river inflows or coastal tidal signals may be unavailable during prediction. It focuses on physics-refined forecasting to improve stability as autoregressive forecast errors accumulate.
See LICENSE file Hydrologic Graph ForecastingSpatiotemporal ForecastingOpen-Boundary Systems

PINNing the Pion: Conformal Deep Learning for Fπ(s) and the Muon g-2 Hadronic Contribution

High-Energy Physics
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 file Physics-Informed Neural Networkpion electromagnetic form factormuon anomalous magnetic moment

PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks

Scientific ML
PINNMorph is an online adaptation framework for physics-informed neural networks that addresses partial differential equation solving by evolving network architecture and major training mechanisms during optimization.
See LICENSE file Physics-Informed Neural NetworksPartial Differential EquationsOnline Adaptation

POIL: Point-Based One-Shot Imitation Learning with Stable Dynamical Systems

Multibody
POIL uses a shared representation to transfer demonstrated manipulation trajectories to novel objects and execute them robustly across changing scenes, grasp configurations, and external disturbances.
See LICENSE file Robotic ManipulationOne-Shot Imitation LearningStable Dynamical Systems

PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation

Geophysics
PR-Smoother is an amortized smoother for prescribed-simulator data assimilation, supporting non-Gaussian posterior estimation over physical state variables in high-dimensional simulators with calibration compatibility.
See LICENSE file Data AssimilationNon-Gaussian SmoothingAmortized Inference

Preconditioned Physics-Informed Neural Operator Training

ScientificML
This paper studies preconditioned training for physics-informed neural operators across general physics simulations, using governing equations rather than solver-generated datasets to reduce offline data-generation cost and enable fresh samples during optimization.
See LICENSE file physics-informed neural operatorpreconditioned trainingscientific machine learning

Prediction of Re-Ignition Times in Dielectric Barrier Discharges

Electromagnetics
A reduced-order physical model describes re-ignition dynamics between consecutive discharges at the same position in dielectric barrier discharge arrangements, enabling time prediction without machine learning.
See LICENSE file dielectric barrier dischargeplasma physicsdischarge dynamics

QPI-DeepONet-MAC: A Scalable and Stable Hybrid Classical-Quantum Architecture for Physics-Informed Deep Operator Networks

ScientificML
The paper develops a hybrid classical-quantum architecture for physics-informed operator learning on parametric partial differential equations, aiming to improve scalability in high dimensions and mitigate trainability difficulties associated with barren plateaus.
See LICENSE file physics-informed DeepONethybrid quantum-classical architecturePDE operator learning

Rate-Agnostic Bioacoustics: Heterogeneous Multi-Taxa Classification with Continuous Filterbanks and Fourier Neural Operators

Acoustics
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 file bioacousticsheterogeneous sampling ratesFourier Neural Operator

Receiver-Side Physics-Informed Residual Digital Twin for Predictive Fine Tracking in Inter-Satellite Optical Links

Electromagnetics
A receiver-side physics-informed residual digital twin for inter-satellite optical links that integrates Gaussian optics and quadrant-photodetector physics with an autoregressive ridge model to predict and compensate residual line-of-sight motion under sensor noise and actuator latency.
See LICENSE file Satellite Optical CommunicationPhysics-Informed Digital TwinLine-of-Sight Tracking

Reduced Cartesian Kinetostatics for Tendon-Driven Continuum Robots: Residual-Stabilized Full-Shape Propagation

Multibody
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 file continuum roboticstendon-driven robotsreduced kinetostatics

Scale-Split Neural Operator for Memory- and Data-Efficient 3D Turbulence Prediction

CFD
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 file Neural Operator3D TurbulenceTurbulence Prediction

SCOPE: Observation-Conditioned Full-Target Prediction for Sparse PDE Inference

ScientificML
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 file PDE inferenceSparse observationsPhysical field reconstruction

Simulator-Refined Diffusion for Radio-Frequency Inverse Design

Electromagnetics
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 file RF PCBInverse DesignDiffusion Models

SINO: Scale-Invariant Neural Operator

ScientificML
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 file scale-invariant neural operatorpartial differential equationsphysics closure

Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins

CFD/Fluid
This study evaluates physics-informed neural networks for atmospheric potential-temperature forecasting, constrained by pressure-coordinate thermodynamic advection-source equations to address short-horizon predictions under sparse thermal observation conditions.
See LICENSE file Physics-Informed Neural NetworksAtmospheric Temperature ForecastingDigital Twins

Sparsely Connected Rank-Inspired Neural Network

ScientificML
SCRINN addresses generic partial differential equations and function approximation through structured sparse connectivity and an orthogonality- and normalization-guided loss that promotes an approximately orthonormal neural basis and progressive evaluation-matrix rank growth.
See LICENSE file Scientific Machine LearningPartial Differential EquationsSparse Neural Networks

Staged Depth Training: A Representation Curriculum for PINNs

ScientificML
This paper introduces a representation curriculum for physics-informed neural networks, implemented through staged depth training that learns representations independently of their predictors and progressively refines them.
See LICENSE file physics-informed neural networksrepresentation curriculumstaged depth training

Stochastic Physics-Constrained Operator Inference for Complex Systems

ScientificML
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 file stochastic operator inferencestochastic differential equationreduced-order modeling

Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision

Materials
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 file Cahn-Hilliard dynamicsFourier neural operatorphase-field simulation

Temporal Interfaces in Metamaterials with Shape-Varying Inclusions

Electromagnetics
This paper develops an analytical and numerical framework for temporal scattering in electromagnetic metamaterials with shape-varying cylindrical inclusions, enabling dynamic control through abrupt geometric transformations of meta-atoms.
See LICENSE file metamaterialstemporal modulationelectromagnetic scattering

Tensor-Train Compressed Separable PINNs: A Curvature-Aware Optimization Framework for Parametric PDEs in High Dimensions

ScientificML
This paper develops a tensor-train compressed separable physics-informed neural network framework for high-dimensional parametric PDEs. It uses a Gauss-Newton pullback metric to provide an operator-informed curvature notion and connects second-order PINN optimization with natural-gradient schemes.
See LICENSE file physics-informed neural networkshigh-dimensional parametric PDEssecond-order optimization

Towards Solving General Relativity with Physics-Informed Neural Networks

ScientificML
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 file Physics-Informed Neural NetworksGeneral RelativityEinstein Equations

U(1) Gauge-Equivariant Representation Learning of Bloch States

Materials
The paper introduces U(1) gauge-equivariant representation learning for mean-field Bloch states, explicitly addressing the gauge redundancy of electronic states in first-principles condensed-matter systems.
See LICENSE file Bloch state representationGauge-equivariant learningCondensed-matter electronic structure

Uncovering Flame Physics with Machine Learning: Application to the Reaction Rate in Hydrogen Flames

CFD
This paper uses convolutional neural networks as analytical tools to investigate relationships between the progress variable field and local chemical source term in lean premixed hydrogen flames. The approach analyzes spatially resolved fields from direct numerical simulations to study combustion reaction-rate physics.
See LICENSE file Hydrogen FlamesCombustion Reaction RateConvolutional Neural Networks

Untangling the Geometry and Speed for RF Sensing Spectrograms

Electromagnetics
This paper establishes a foundation for physically interpretable RF sensing that disentangles reflector speed from geometry, jointly recovering speed, geometry factor, relative amplitude, and width of dominant Doppler ridges for improved applicability in unconstrained real-world settings.
See LICENSE file RF sensingDopplerelectromagnetic sensing

Warm-Starting PDE Solvers with Any-Dimensional Machine Learning

ScientificML
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 file PDE solverany-dimensional learningzero-shot transfer

Wave Breaking and Structure-Preserving Fully Discrete Method for Stochastic Camassa–Holm Equation with Additive Noise

Fluid Dynamics
This paper studies wave breaking and a structure-preserving fully discrete method for the stochastic Camassa–Holm equation, a nonlinear shallow-water wave model with additive random forcing. It analyzes finite-time wave breakdown and derives an initial-slope condition under an additional moment assumption.
See LICENSE file Stochastic shallow-water wavesCamassa–Holm equationWave breaking

When Does Domain Adaptation Help on Physical Vibration Sensors? A Held-Out-Bearing Study of Neural-Operator and Convolutional Models

Structural
This paper studies rolling-element bearing fault diagnosis from vibration, a physical-sensing task, under operating-condition shift and a held-out-bearing protocol. It compares neural-operator and convolutional models while assigning each physical bearing entirely to either training or testing.
See LICENSE file Bearing Vibration DiagnosisDomain AdaptationNeural Operators

When Does the Moment Basis Matter in Lattice Boltzmann Methods?

CFD
This paper analyzes when orthogonalizing the moment basis changes a central-moment lattice Boltzmann scheme, showing the effect is governed by the geometry of the velocity set: two bases related by a constant matrix define the same scheme only if the commutator condition holds, and on physical states only its columns matter.
See LICENSE file lattice Boltzmann methodcentral-moment schememoment basis

Where Should Physics Enter a Molecular Crystal Generator?

Materials
CrystAF studies where physics should enter all-atom molecular crystal generation by comparing training, post-training, and inference strategies with the generator and physical signal held fixed.
See LICENSE file Molecular crystalsGenerative modelingInteratomic potential

Physics-Informed Learning Annual Review 2025-2026

Annual Survey / Physics-Informed Learning
A systematic review of 2025-2026 progress in physics-informed ML - neural operators, diffusion for PDE solving, large benchmarks and industrial deployment.
Various SurveyPhysics-InformedPINN