Paris Perdikaris — accepted AI-conference papers

2026

Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuators

Gregory Campbell, Gentian Muhaxheri, Leonardo Ferreira Guilhoto, Christian Santangelo, Paris Perdikaris, James Pikul +1

ICRA 2026poster

Soft pneumatic actuators (SPA) made from elastomeric materials can provide large strain and large force. The behavior of locally strain-restricted hyperelastic materials under inflation has been investigated thoroughly for shape reconfiguration, but requires further investigation for trajectories in…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2026

CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators

Xianglong Hou, Xinquan Huang, Paris Perdikaris

ICLR 2026poster

Neural operator surrogates for time-dependent partial differential equations (PDEs) conventionally employ autoregressive prediction schemes, which accumulate error over long rollouts and require uniform temporal discretization. We introduce the Continuous Flow Operator (CFO), a framework that learns…

Cited by 0 Source ↗Scholar ↗

2026

PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations

Xinquan Huang, Paris Perdikaris

AAAI 2026technical

Neural networks have emerged as powerful surrogates for solving partial differential equations (PDEs), offering significant computational speedups over traditional methods. However, these models suffer from a critical limitation: error accumulation during long-term rollouts, where small inaccuracies

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

CViT: Continuous Vision Transformer for Operator Learning

Sifan Wang, Jacob H Seidman, Shyam Sankaran, Hanwen Wang, George J. Pappas, Paris Perdikaris

ICLR 2025poster

Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various physical domains. Here we introduce the Continuous Vision Transformer (CViT), a novel neural operator architecture that…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Deep Learning Alternatives Of The Kolmogorov Superposition Theorem

Leonardo Ferreira Guilhoto, Paris Perdikaris

ICLR 2025spotlight

This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original KST formulation, while mathematically elegant, presents practical challenges due to its limited insight into the structure of inner and outer functions a…

Cited by 8 Source ↗PDF ↗Scholar ↗

2025

Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective

Sifan Wang, Ananyae Kumar bhartari, Bowen Li, Paris Perdikaris

NeurIPS 2025poster

Physics-informed neural networks (PINNs) have shown significant promise in computational science and engineering, yet they often face optimization challenges and limited accuracy. In this work, we identify directional gradient conflicts during PINN training as a critical bottleneck. We introduce a n…

Cited by 0 Source ↗code ↗Scholar ↗

2024

On conditional diffusion models for PDE simulations

Aliaksandra Shysheya, Cristiana Diaconu, Federico Bergamin, Paris Perdikaris, José Miguel Hernández-Lobato, Richard E. Turner +1

NeurIPS 2024poster

Modelling partial differential equations (PDEs) is of crucial importance in science and engineering, and it includes tasks ranging from forecasting to inverse problems, such as data assimilation. However, most previous numerical and machine learning approaches that target forecasting cannot be appli…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling

Arka Daw, Jie Bu, Sifan Wang, Paris Perdikaris, Anuj Karpatne

ICML 2023poster

Despite the success of physics-informed neural networks (PINNs) in approximating partial differential equations (PDEs), PINNs can sometimes fail to converge to the correct solution in problems involving complicated PDEs. This is reflected in several recent studies on characterizing the "failure mode…

Cited by 69 Source ↗PDF ↗code ↗Scholar ↗

2023

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

Phillip Lippe, Bastiaan S. Veeling, Paris Perdikaris, Richard E Turner, Johannes Brandstetter

NeurIPS 2023spotlight

Time-dependent partial differential equations (PDEs) are ubiquitous in science and engineering. Recently, mostly due to the high computational cost of traditional solution techniques, deep neural network based surrogates have gained increased interest. The practical utility of such neural PDE solver…

Cited by 77 Source ↗PDF ↗Scholar ↗

2023

Variational Autoencoding Neural Operators

Jacob H Seidman, Georgios Kissas, George J. Pappas, Paris Perdikaris

ICML 2023poster

Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. A natural way of modeling functional data is by learning operators between infinite dimensional spaces, leading to discretizati…

Cited by 15 Source ↗PDF ↗Scholar ↗

2022

NOMAD: Nonlinear Manifold Decoders for Operator Learning

Jacob H Seidman, Georgios Kissas, Paris Perdikaris, George J. Pappas

NeurIPS 2022accept

Supervised learning in function spaces is an emerging area of machine learning research with applications to the prediction of complex physical systems such as fluid flows, solid mechanics, and climate modeling. By directly learning maps (operators) between infinite dimensional function spaces, the…

Cited by 93 Source ↗PDF ↗Scholar ↗