ICLR 2024 Past AI for science
ICLR 2024 Workshop on AI4DifferentialEquations In Science
AI4DiffEqtnsInSci @ ICLR 2024
- Submission deadline
- Feb 11, 2024, 12:00 UTC imported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Auto-imported from the OpenReview venue record on 2026-06-10 — please verify and enrich (topics are keyword-guessed).
Accepted papers (87)
Fetched from OpenReview (v2) on 2026-06-10.
-
A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics
-
A Novel ML Model for Numerical Simulations Leveraging Fourier Neural Operators
-
A PHYSICS-INFORMED NEURAL NETWORK FOR COUPLED CALCIUM DYNAMICS IN A CABLE NEURON
-
Accelerating Neural Differential Equations for Irregularly-Sampled Dynamical Systems Using Variational Formulation
-
Adaptive Multilevel Neural Networks for Parametric PDEs with Error Estimation
-
Application of gauge equivariant convolutional neural networks to learning a fixed point action for SU(3) gauge theory
-
Application of Neural Ordinary Differential Equations for Tokamak Plasma Dynamics Analysis
-
Applications of Fourier Neural Operators in the Ifmif-Dones Accelerator
-
Approximating Family of Steep Traveling Wave Solutions to Fisher's Equation with PINNs
-
AutoBasisEncoder: Pre-trained Neural Field Basis via Autoencoding for Operator Learning
-
CHAROT: Robustly controlling chaotic PDEs with partial observations
-
CLIFFORD NEURAL OPERATORS ON ATMOSPHERIC DATA INFLUENCED PARTIAL DIFFERENTIAL EQUATIONS
-
Comparing and Contrasting Deep Learning Weather Prediction Backbones on Navier-Stokes Dynamics
-
Comparing PINNs Across Frameworks: JAX, TensorFlow, and PyTorch
-
Conformalized Physics-Informed Neural Networks
-
Consistency Matters: Neural ODE Parameters are Dependent on the Training Numerical Method
-
Continuous-time neural networks for modeling linear dynamical systems
-
Data-Driven Higher Order Differential Equations Inspired Graph Neural Networks
-
Data-driven Multi-Fidelity Modelling for Time-dependent Partial Differential Equations using Convolutional Neural Networks
-
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
-
DOF: Accelerating High-order Differential Operators with Forward Propagation
-
Efficient Fourier Neural Operators by Group Convolution and Channel Shuffling
-
Efficient GPU-Accelerated Global Optimization for Inverse Problems
-
Ensemble learning for Physics Informed Neural Networks: a Gradient Boosting approach
-
Equivariant Neural Fields For Symmetry Preserving Continous PDE Forecasting
-
Estimating Field Parameters from Multiphysics Governing Equations with Scarce Data
-
Extending Deep Learning Emulation Across Parameter Regimes to Assess Stochastically Driven Spontaneous Transition Events
-
Extension of Physics-informed Neural Networks to Solving Parameterized PDEs
-
FastVPINNs: A fast, versatile and robust Variational PINNs framework for forward and inverse problems in science
-
GA-ReLU: an activation function for Geometric Algebra Networks applied to 2D Navier-Stokes PDEs
-
Galerkin meets Laplace: Fast uncertainty estimation in neural PDEs
-
Generative PDE Control
-
Guided Autoregressive Diffusion Models with Applications to PDE Simulation
-
Hessian Reparametrization for Coarse-grained Energy Minimization
-
Heteroscedastic uncertainty quantification in Physics-Informed Neural Networks
-
Hierarchy-based Clifford Group Equivariant Message Passing Neural Networks
-
INTEGRAL PINNS FOR HYPERBOLIC CONSERVATION LAWS
-
Integrating Kernel Methods and Deep Neural Networks for Solving PDEs
-
Investigating the effects of plant diversity on soil thermal diffusivity using Physics- Informed Neural Networks
-
Investigation of Latent Time-Scales in Neural ODE Surrogate Models
-
Investigation of Numerical Diffusion in Aerodynamic Flow Simulations with Physics Informed Neural Networks
-
JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework
-
Joint Parameter and Parameterization Inference with Uncertainty Quantification Through Differentiable Programming
-
Latent Diffusion Transformer with Local Neural Field as PDE Surrogate Model
-
LEARN TO ADAPT PARAMETRIC SOLVERS UNDER INCOMPLETE PHYSICS
-
Learning a vector field from snapshots of unidentified particles rather than particle trajectories
-
Learning iterative algorithms to solve PDEs.
-
Learning Stochastic Dynamics from Data
-
Learning The Delay in Delay Differential Equations
-
Learning time-dependent PDE via graph neural networks and deep operator network for robust accuracy on irregular grids
-
Mathematical Modeling of Spatio-Temporal Disease Spreading Using PDEs for Machine Learning
-
Mechanistic Neural Networks for Scientific Machine Learning
-
Minimizing Structural Vibrations via Guided Diffusion Design Optimization
-
Mixture of Neural Operators: Incorporating Historical Information for Longer Rollouts
-
Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows
-
Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layers
-
MultiSTOP: Solving Functional Equations with Reinforcement Learning
-
Neural Context Flows for Learning Generalizable Dynamical Systems
-
Neural Langevin-type Stochastic Differential Equations for Astronomical time series Classification under Irregular Observations
-
Neural ODE for Multi-channel Attribution
-
Neural operators with localized integral and differential kernels
-
Neural Parameter Regression for Explicit Representations of PDE Solution Operators
-
Neural SPH: Improved Neural Modeling of Lagrangian Fluid Dynamics
-
On Representing Electronic Wave Functions with Sign Equivariant Neural Networks
-
On training Physics-Informed Neural Networks for Oscillating Problems
-
Optimal Experimental Design for Bayesian Inverse Problems using Energy-Based Couplings
-
Optimizing Computationally-Intensive Simulations Using a Biologically-Inspired Acquisition Function and a Fourier Neural Operator Surrogate
-
PDEformer: Towards a Foundation Model for One-Dimensional Partial Differential Equations
-
Physics-constrained DeepONet for Surrogate CFD models: a curved backward-facing step case
-
Physics-Informed Koopman Network for time-series prediction of dynamical systems
-
Physics-Informed Machine Learning for Fluid Flow Prediction in Porous Media
-
Physics-informed neural networks for sampling
-
PINA: a PyTorch Framework for Solving Differential Equations by Deep Learning for Research and Production Environments
-
PointSAGE: Mesh-independent superresolution approach to fluid flow predictions
-
RBF-PINN: NON-FOURIER POSITIONAL EMBEDDING IN PHYSICS-INFORMED NEURAL NETWORKS
-
Scaling Transformers for Skillful and Reliable Medium-range Weather Forecasting
-
Semiparametric Inference and Equation Discovery with the Bayesian Machine Scientist
-
Solving Poisson Equations using Neural Walk-on-Spheres
-
Targeted Reduction of Causal Models
-
The conjugate kernel for efficient training of physics-informed deep operator networks
-
Traversing Chemical Space with Latent Potential Flows
-
TUCKER DECOMPOSITION FOR INTERPRETABLE NEURAL ORDINARY DIFFERENTIAL EQUATIONS
-
Uncertainty Quantification for Fourier Neural Operators
-
Vectorized Conditional Neural Fields: A Framework for Solving Time-dependent PDEs
-
Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models
-
XDDPM: EXPLAINABLE DENOISING DIFFUSION PROB- ABILISTIC MODEL FOR SCIENTIFIC MODELING
-
Zebra: a continuous generative transformer for solving parametric PDEs