ICLR 2026PastOther
AI&PDE: ICLR 2026 Workshop on AI and Partial Differential Equations
AI&PDE
- Submission deadline
- Feb 11, 2026, 23:59 UTCOpenReview-synced 2026-02-11 23:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (111)
Fetched from OpenReview (v2) on 2026-06-10.
(U)NFV: (Un)Supervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
$PINN - a Domain Decomposition Method for Bayesian Physics-Informed Neural Networks
3D-PINNS: A UNIFIED FRAMEWORK FOR DIMENSION-WISE INTERPRETABILITY AND ADAPTIVE DOMAIN DECOMPOSITION
A Conservation Law Perspective on Explainability in Spiking Neural Networks
A Data-Parallel Additively Preconditioned Trust-Region Strategy for Physics-Informed Neural Networks
A Multigrid-inspired Neural Iterative Solver for Poisson Equations on Large Voxel Grids
A Neural Score-Based Method for Deterministic Collisional Plasma Simulation
AB-PIELMS: ADAPTIVE-BASIS PHYSICS-INFORMED EXTREME LEARNING MACHINES FOR RESIDUAL-DRIVEN DOMAIN DECOMPOSITION
Accelerating PINN Training via RL-based Adaptive Loss Control
Adaptive SDE Interpolants for Calibrated Probabilistic PDE Forecasting
Adaptive Test-Time Compute Allocation for Neural PDE Solvers
Adaptive Tokenization for Vision Transformer PDE Simulation
Astral: training physics-informed neural networks with error majorants
ATTENTION-ENHANCED NEURAL OPERATOR FOR VARIABLE-TIMESTEP PREDICTION OF PDES
AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
Born-Series-Inspired Residual Metric for Learned Preconditioners
Causal Field Theory: Causal Semantics for PDE-Based Spatio-Temporal Systems
Chebyshev-Augmented One-Shot Transfer Learning for PINNs on Nonlinear Differential Equations
CHLU: The Causal Hamiltonian Learning Unit as a Symplectic Primitive for Deep Learning
COARSERL: A GRAPH REINFORCEMENT LEARNING METHOD FOR ALGEBRAIC MULTIGRID COARSENING
Compositional Neural Operators for Multi-Dimensional Fluid Dynamics
Constructing Machine-Precision Neural Networks with Quasi-Interpolants
Data-Efficient Neural Operator Training via Physics-Based Active Learning
Decoding Partial Differential Equations: Cross-Modal Adaptation of Decoder-only Models to PDEs
Decoupled Diffusion Solver for Inverse Problems on Function Spaces
Deep Learning Based Surrogate Modeling of PDE Governed Systems Using Fourier Neural Operators (FNOs): Application to Clarifier Dynamics in Wastewater Treatment
Direct Learning of Calibration-Aware Uncertainty for Neural PDE Surrogates
Discovering Bäcklund Transformations with PDE Foundation Models
Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets
ECLIPSE: A Composable Pipeline for Predicting ecDNA Formation, Evolution, and Therapeutic Vulnerabilities in Cancer
Empirical Stability Analysis of Kolmogorov-Arnold Networks in Hard-Constrained Recurrent Physics-Informed Discovery
EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs
Evolutionary Two-Stage Hyperparameter Optimization Strategies for Physics-Informed Neural Networks
Fast Multiscale PDE Solvers via Multilevel Domain Decomposition and Random Features
Fast, Convex and Conditioned Single-Layer Network for Learning Multi-Fidelity Univariate Data and Linear Differential Equations
FastLSQ: Solving PDEs in One Shot via Fourier Features with Exact Analytical Derivatives
Flow-Matching Sampling in Physics-Informed Neural Networks for PDEs with Sharp Source Terms
Fourier Neural Operators for Geodynamic Modeling: A Hybrid Surrogate–Solver Framework
From Large-Scale Winds to Urban Decision Making: A Cross-Scale Framework for Wind-Aware UAV Navigation
From RawTokens to PhysSummary: Probing Text Interfaces for Inverse 1D PDE Parameter Estimation
Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage
Generalization Analysis and Improved Shape Representation with Neural Signed Distance Functions
Gradient Scaling Effects In Adaptive Spectral PINNs For Stiff Nonlinear ODEs
Green's Neural Operator with Neumann conditions for EMG volume conductor modelling
HyperKKL: Enabling Non-Autonomous State Estimation through Dynamic Weight Conditioning
Intrinsic Green's Learning: Supervised Learning on Manifolds via Inverse PDE
Kernel-Adaptive Physics-Informed Shallow Meta-Learning for Parametric Linear PDEs
Kinetic-based regularization: Learning spatial derivatives and PDE applications
Kraus Constrained Sequence Learning For Quantum Trajectories from Continuous Measurement
Late Fusion Neural Operators for Parameterized Partial Differential Equations
Latent Reciprocity Representation: Bidirectional Latent-Space Alignment as Physics-Aware Regularization for Neural Operators
Learning Dengue Dynamics through Hybrid Equation-Guided and Data-Driven Models
LEARNING EMBEDDINGS OF NON-LINEAR PDES: THE BURGERS’ EQUATION
Learning Heat-Based Equations in Self-Similar Variables
Learning Mesh-Free Discrete Differential Operators with Self-Supervised Graph Neural Networks
Learning Parameterized Nonlinear Elasticity on Curved Surfaces
Learning Spatially-Varying Fractional Orders in PDEs
Learning Where the Physics Is: Probabilistic Adaptive Sampling for Stiff PDEs
Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity
Limits of Resolution Equivariance in Fourier Neural Operators
LLM-Driven Loss Balancing for Physics-Informed Neural Networks
Momentum-Accelerated Structured Preconditioning for Physics-Informed Neural Networks
mPOD-DeepONet: POD-DeepONet for Multiple Outputs
Multi-Trajectory Physics-Informed Neural Networks for HJB Equations with Hard Terminal Constraints: Optimal Execution and High-Dimensional LQR
Neural Bloch Eigensolver for Honeycomb Lattices
Neural Geometry for PDEs: Regularity, Stability, and Convergence Guarantees
Neural likelihood surrogates for parameter inference via log-density PDE
Neural operators for varying geometry in the forward EMG model.
Neural-VSI: Variational System Identification of Structural Parameter Fields in High-Order PDEs
Neuro-Spectral Architectures with Time-Domain Decomposition
On the Value of Tokeniser Pretraining in Physics Foundation Models
One Operator to Rule Them All? On Boundary-Indexed Operator Families in Neural PDE Solvers
OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference
OtterWeather: Highly Skillful Medium-Range Weather Forecasting on a Single GPU
Out-of-distribution generalization of deep-learning surrogates for 2D PDE-generated dynamics in the small-data regime
Out-of-distribution transfer of PDE foundation models to material dynamics under extreme loading
Particle-Guided Diffusion for Gas-Phase Reaction Kinetics
Physics Informed Neural Networks for Magnetohydrodynamic Equations
Physics-Constrained Neural Networks for Improved Short-Term Weather Forecasting: A Case Study over the South Pacific
Physics-Constrained Stochastic ROMs for Unsteady Airfoil Flows
Physics-Informed Adaptive Training for 3D Acoustic Wave Propagation
Physics-Informed Conditional Diffusion for Multi-Modal PDEs
Physics-Informed Deep B-Spline Networks
Physics-informed fine-tuning of foundation models for partial differential equations
Physics-Informed Shearlet Neural Operator (PI-ShearletNO) for parametric partial differential equations
Point Cloud Sequence Encoding for Material-conditioned Graph Network Simulators
POSEIDON: POSEIDON: Physics-Optimized Seismic Energy Inference and Detection Operating Network
PRESS: Physics-Regularized Parameter Estimation from Steady-State Turing Patterns
Probabilistic residual transport between multi-fidelity manifolds
Probabilistic Retrofitting of Learned Simulators
Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision
Reinforcement Learning Agent for PINN Optimizer Chains
Relative Position Biases for Transformer PINNs
Representation Learning for Spatiotemporal Physical Systems
Resolving Extreme Data Scarcity by Explicit Physics Integration: An Application to Groundwater Heat Transport
Semi-Lagrangian Physics-Informed Neural Networks (SL-PINNs) for solving hyperbolic Partial Differential Equations (PDEs)
Smoothness Errors in Dynamics Models and How to Avoid Them
SoL-DeepONet: Solver-In-The-Loop Deep Operator Networks for Parametric PDEs
Split Conformal Prediction in the Function Space via Neural Operator Learning
Supervised Metric Regularization Through Alternating Optimization for Multi-Regime Physics-Informed Neural Networks
Text-Trained LLMs Can Zero-Shot Extrapolate PDE Dynamics, Revealing a Three-Stage In-Context Learning Mechanism
The Fractal Neural Operator: Overcoming Spectral Bias in Chaotic Attractors via Prime-Harmonic Weierstrass Encodings
Time-Splitting Fourier Neural Operator with Coordinate Injection for Scalable Reservoir Simulation
TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
TOWARD THE THERMODYNAMIC LIMIT: NEURAL OPERATORS FOR NON-EQUILIBRIUM DYNAMICS OF MOTT INSULATORS
Towards Efficient and Stable Ocean State Forecasting: A Continuous-Time Koopman Approach
Towards Uncertainty Quantification in Data-Driven Reduced-Order Models via Bayesian Graph Neural Networks
UNED: One-shot Uncertainty-aware Neural Experimental Design for Transient PDEs
Universal Diffusion-Based Probabilistic Downscaling
What Does a Neural PDE Solver Really Learn? A Residual-Spectrum Diagnostic
When Does Physics Help? A Systematic Study of Physics-Guided Learning for Robotic Contact Dynamics