1.1k citations · 7.2k across the 70 of their papers we have counts for
77 papers
Multimodal Interaction Estimation for Contact-Aware Adaptive Impedance Control
Mateusz Jaszczuk, Paris Perdikaris, Nadia Figueroa
With advancements in learning-based policies, robots are increasingly being deployed in human-centric environments, such as manufacturing floors and homes, where safe and precise o…
Operator-informed initialization for Fourier features physics-informed neural networks
Juan Molina, Paris Perdikaris, Mircea Petrache +2
Physics-Informed Neural Networks (PINNs) typically exhibit spectral bias, where some frequencies of the target function converge more slowly than others. In this work, we analyze t…
SIFARI: Self-Supervised Interferometric Fitting for Astronomical Radio Imaging
Shunyuan Mao, Andrea Isella, Paris Perdikaris +2
Radio-interferometric images are reconstructed from sparsely sampled visibilities, and CLEAN-based imaging can struggle with spatial filtering, complex morphologies, and uncertaint…
Physics-Informed Learning of Feedback-Linearizing Representations
Pavlos Kallinikidis, Fengjun Yang, David Snyder +4
Feedback linearization is a powerful tool in nonlinear control, but finding the linearizing coordinate transform remains challenging. Feedback linearizing transforms are governed b…
A Physics-Conditioned Neural Operator for Generalization of Atrioventricular Valve Mechanics across Pressure and Tissue Properties
Shawn Koohy, Wensi Wu, Matthew A Jolley +1
Mitral and tricuspid regurgitation are the most common regurgitant valvular lesions, yet only a minority of severe cases undergo corrective surgery. Rapid assessment of valve mecha…
Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime Physics
Hanwen Wang, Paris Perdikaris
Physics-informed neural networks (PINNs) struggle on PDEs whose governing physics varies across the domain. We trace this to a structural property of standard coordinate networks:…
Small Models, Strong Priors: Architectural Inductive Bias for Parameter-Efficient Neural PDE Solvers
Shyam Sankaran, Hanwen Wang, Paris Perdikaris
Neural PDE solvers have followed the scaling trajectory of vision and language, with recent foundation models reaching billions of parameters. We argue that scale is a poor substit…
A Mutual Information Lower Bound for Multimodal Regression Active Learning
Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris Perdikaris
Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is multimodal: variance misses moda…
When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions
Sifan Wang, Shawn Koohy, Yiping Lu +1
Physics-informed neural networks (PINNs) provide a promising machine learning framework for solving partial differential equations, but their training often breaks down on challeng…
Self-Flow-Matching assisted Full Waveform Inversion
Xinquan Huang, Paris Perdikaris
Full-waveform inversion (FWI) is a high-resolution seismic imaging method that estimates subsurface velocity by matching simulated and recorded waveforms. However, FWI is highly no…
Multimodal Scientific Learning Beyond Diffusions and Flows
Leonardo Ferreira Guilhoto, Akshat Kaushal, Paris Perdikaris
Scientific machine learning (SciML) increasingly requires models that capture multimodal conditional uncertainty arising from ill-posed inverse problems, multistability, and chaoti…
CFO: Learning Continuous-Time PDE Dynamics via Flow-Matched Neural Operators
Xianglong Hou, Xinquan Huang, Paris Perdikaris
Neural operator surrogates for time-dependent partial differential equations (PDEs) conventionally employ autoregressive prediction schemes, which accumulate error over long rollou…
Neural Networks as Surrogate Solvers for Time-Dependent Accretion Disk Dynamics
Shunyuan Mao, Weiqi Wang, Sifan Wang +7
Accretion disks are ubiquitous in astrophysics, appearing in diverse environments from planet-forming systems to X-ray binaries and active galactic nuclei. Traditionally, modeling…
Simulating Three-dimensional Turbulence with Physics-informed Neural Networks
Sifan Wang, Shyam Sankaran, Xiantao Fan +2
Turbulent fluid flows are among the most computationally demanding problems in science, requiring enormous computational resources that become prohibitive at high flow speeds. Phys…
PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations
Xinquan Huang, Paris Perdikaris
Neural networks have emerged as powerful surrogates for solving partial differential equations (PDEs), offering significant computational speedups over traditional methods. However…
Active Learning Design: Modeling Force Output for Axisymmetric Soft Pneumatic Actuators
Gregory M. Campbell, Gentian Muhaxheri, Leonardo Ferreira Guilhoto +4
Soft pneumatic actuators (SPA) made from elastomeric materials can provide large strain and large force. The behavior of locally strain-restricted hyperelastic materials under infl…
Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
Sifan Wang, Ananyae Kumar Bhartari, Bowen Li +1
Multi-task learning through composite loss functions is fundamental to modern deep learning, yet optimizing competing objectives remains challenging. We present new theoretical and…
On conditional diffusion models for PDE simulations
Aliaksandra Shysheya, Cristiana Diaconu, Federico Bergamin +4
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 dat…
Score Neural Operator: A Generative Model for Learning and Generalizing Across Multiple Probability Distributions
Xinyu Liao, Aoyang Qin, Jacob Seidman +3
Most existing generative models are limited to learning a single probability distribution from the training data and cannot generalize to novel distributions for unseen data. An ar…
Deep Learning Alternatives of the Kolmogorov Superposition Theorem
Leonardo Ferreira Guilhoto, Paris Perdikaris
This paper explores alternative formulations of the Kolmogorov Superposition Theorem (KST) as a foundation for neural network design. The original KST formulation, while mathematic…
Disk2Planet: A Robust and Automated Machine Learning Tool for Parameter Inference in Disk-Planet Systems
Shunyuan Mao, Ruobing Dong, Kwang Moo Yi +3
We introduce Disk2Planet, a machine learning-based tool to infer key parameters in disk-planet systems from observed protoplanetary disk structures. Disk2Planet takes as input the…
Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials
Sifan Wang, Tong-Rui Liu, Shyam Sankaran +1
Heterogeneous materials, crucial in various engineering applications, exhibit complex multiscale behavior, which challenges the effectiveness of traditional computational methods.…
Physics-Informed Neural Networks and Extensions
Maziar Raissi, Paris Perdikaris, Nazanin Ahmadi +1
In this paper, we review the new method Physics-Informed Neural Networks (PINNs) that has become the main pillar in scientific machine learning, we present recent practical extensi…
CViT: Continuous Vision Transformer for Operator Learning
Sifan Wang, Jacob H Seidman, Shyam Sankaran +3
Operator learning, which aims to approximate maps between infinite-dimensional function spaces, is an important area in scientific machine learning with applications across various…