A Creator-Inspector multi-agent LLM pipeline for constitutive artificial neural networks increases the rate of models satisfying all nine physical constraints to 100% or 56% depending on the LLM backbone.
arXiv preprint arXiv:2211.08064 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
AOT-POT adaptively reshapes complex PDE solution operators via input-dependent transformations and parallel stream mixing to enable effective large-scale pre-training, yielding SOTA results on 12 benchmarks with minimal added parameters.
ST-PT turns transformers into explicit factor graphs for time series, enabling structural injection of symbolic priors, per-sample conditional generation, and principled latent autoregressive forecasting via MFVI iterations.
MH-PINN compactifies unbounded domains with mapping and enforces wave boundary conditions through network architecture for efficient, accurate simulations.
A physics-informed MLP reconstructs high-fidelity 4D spectra from only 1/32 of the samples in experimental 2DIR hyperspectral imaging.
Graph-based summary statistics on pulsar timing residuals detect SGWB down to strain amplitude 1.2e-15 and yield 2.3 sigma evidence in NANOGrav 15-year data via clustering coefficient and edge weight measures.
Introduces Laplace-approximated Bayesian PINNs for automatic loss-weight optimization when solving PDEs such as heat, wave, and Burgers equations.
citing papers explorer
-
LLM-driven design of physics-constrained constitutive models: two agents are better than one
A Creator-Inspector multi-agent LLM pipeline for constitutive artificial neural networks increases the rate of models satisfying all nine physical constraints to 100% or 56% depending on the LLM backbone.
-
AOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training
AOT-POT adaptively reshapes complex PDE solution operators via input-dependent transformations and parallel stream mixing to enable effective large-scale pre-training, yielding SOTA results on 12 benchmarks with minimal added parameters.
-
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
ST-PT turns transformers into explicit factor graphs for time series, enabling structural injection of symbolic priors, per-sample conditional generation, and principled latent autoregressive forecasting via MFVI iterations.
-
Mapping-based Hard-constrained Physics-Informed Neural Networks for unbounded wave problems
MH-PINN compactifies unbounded domains with mapping and enforces wave boundary conditions through network architecture for efficient, accurate simulations.
-
Accelerating 4D Hyperspectral Imaging through Physics-Informed Neural Representation and Adaptive Sampling
A physics-informed MLP reconstructs high-fidelity 4D spectra from only 1/32 of the samples in experimental 2DIR hyperspectral imaging.
-
Graph-based Summary Statistics for Revealing the Stochastic Gravitational Wave Background in Pulsar Timing Arrays
Graph-based summary statistics on pulsar timing residuals detect SGWB down to strain amplitude 1.2e-15 and yield 2.3 sigma evidence in NANOGrav 15-year data via clustering coefficient and edge weight measures.
-
Bayesian Reasoning for Physics Informed Neural Networks
Introduces Laplace-approximated Bayesian PINNs for automatic loss-weight optimization when solving PDEs such as heat, wave, and Burgers equations.