FOSSA scores sensor importance for PINN inverse problems via first-order optimality conditions at convergence and shows that low-importance sensors can degrade reconstruction accuracy in electrocardiographic imaging.
hub
Physics-informed machine learning
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
verdicts
UNVERDICTED 12roles
background 3polarities
background 3representative citing papers
A PINN embedding Cosserat rod mechanics achieves sub-1% mean shape error for 6-DoF concentric tube robots using minimal training data and outperforms a pure physics baseline.
Pi-PINN learns transferable physics-informed representations and solves known or unseen PDEs via closed-form pseudoinverse head adaptation, achieving 100-1000x faster predictions and 10-100x lower error than standard PINNs or data-driven models even with minimal training samples.
LASS-ODE-Power is a pretrained model that predicts power-system dynamic trajectories across regimes in a zero-shot manner after large-scale ODE pretraining and targeted fine-tuning.
TIGER delivers the first GPU-accelerated high-precision TFHE implementations for LLM nonlinear layers, with measured speedups of 7.17x for GELU, 16.68x for Softmax, and 17.05x for LayerNorm over CPU baselines.
MAG-Net integrates radar dynamics with satellite IR, WV, and BTD channels via dual-stream encoding and uncertainty-weighted decoding to raise CSI40 by 0.083 over prior baselines for intense convective events.
A neural network framework incorporating compositional structure achieves modular identifiability for genetic circuit modules, learning their functions with reduced data and providing theoretical guarantees plus out-of-distribution prediction.
A distilled physics-informed neural surrogate in a hierarchical optimal control architecture raises simulated PIT success from 63.8% to 76.7% and succeeds in three of four low-speed scaled-vehicle tests.
Indirect PINN methods for semilinear PDE optimal control preserve the state equation and optimality conditions more faithfully than direct PINNs while producing smoother controls due to implicit regularization.
A physics-informed neural network for pouch cell temperature estimation achieves 49.1% lower mean squared error and faster convergence than a purely data-driven model on varying cooling geometries.
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.
A tutorial organizes learning-based radio map construction around data sources, neural architectures, and physics-awareness integration for wireless environments.
citing papers explorer
-
FOSSA: First-Order Optimality-Based Sensor Selection for PINN Inverse Problems, with Application to Electrocardiographic Imaging
FOSSA scores sensor importance for PINN inverse problems via first-order optimality conditions at convergence and shows that low-importance sensors can degrade reconstruction accuracy in electrocardiographic imaging.
-
Few-Shot Physics-Informed Neural Network for Shape Reconstruction of Concentric-Tube Robots
A PINN embedding Cosserat rod mechanics achieves sub-1% mean shape error for 6-DoF concentric tube robots using minimal training data and outperforms a pure physics baseline.
-
Transferable Physics-Informed Representations via Closed-Form Head Adaptation
Pi-PINN learns transferable physics-informed representations and solves known or unseen PDEs via closed-form pseudoinverse head adaptation, achieving 100-1000x faster predictions and 10-100x lower error than standard PINNs or data-driven models even with minimal training samples.
-
Predicting Power-System Dynamic Trajectories with Foundation Models
LASS-ODE-Power is a pretrained model that predicts power-system dynamic trajectories across regimes in a zero-shot manner after large-scale ODE pretraining and targeted fine-tuning.
-
GPU Acceleration of TFHE-Based High-Precision Nonlinear Layers for Encrypted LLM Inference
TIGER delivers the first GPU-accelerated high-precision TFHE implementations for LLM nonlinear layers, with measured speedups of 7.17x for GELU, 16.68x for Softmax, and 17.05x for LayerNorm over CPU baselines.
-
MAG-Net: Physics-Aware Multi-Modal Fusion of Geostationary Satellite and Radar for Severe Convective Precipitation Nowcasting
MAG-Net integrates radar dynamics with satellite IR, WV, and BTD channels via dual-stream encoding and uncertainty-weighted decoding to raise CSI40 by 0.083 over prior baselines for intense convective events.
-
Learning Genetic Circuit Modules with Neural Networks: Full Version
A neural network framework incorporating compositional structure achieves modular identifiability for genetic circuit modules, learning their functions with reduced data and providing theoretical guarantees plus out-of-distribution prediction.
-
Physics-Informed Neural Optimal Control for Precision Immobilization Technique in Emergency Scenarios
A distilled physics-informed neural surrogate in a hierarchical optimal control architecture raises simulated PIT success from 63.8% to 76.7% and succeeds in three of four low-speed scaled-vehicle tests.
-
PINNs in PDE Constrained Optimal Control Problems: Direct vs Indirect Methods
Indirect PINN methods for semilinear PDE optimal control preserve the state equation and optimality conditions more faithfully than direct PINNs while producing smoother controls due to implicit regularization.
-
Physics-Informed Machine Learning for Pouch Cell Temperature Estimation
A physics-informed neural network for pouch cell temperature estimation achieves 49.1% lower mean squared error and faster convergence than a purely data-driven model on varying cooling geometries.
-
Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization
The paper reviews and extends energy-based dynamical models that use gradient flows and energy landscapes for neurocomputation, learning, and optimization tasks.
-
A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness
A tutorial organizes learning-based radio map construction around data sources, neural architectures, and physics-awareness integration for wireless environments.