LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
Multiple physics pretraining for physical surrogate models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative 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.
A hybrid transformer-FEM integrator provides provable discrete energy preservation and gradient bounds for stable autoregressive forecasting of chaotic systems, with 65x fewer parameters and 9000x speedup in a fusion surrogate trained on 12 simulations.
A multimodal SwinV2-UNet vision transformer conditioned on data modality and time predicts spatiotemporal fluid flows and reconstructs unobserved fields from limited views using CFD data of argon jet injection.
Flow Marching jointly samples noise and physical time to learn a velocity field for generative PDE modeling, paired with a latent autoencoder and efficient transformer for large-scale pretraining on 2.5M trajectories.
Multiple Neural Operators achieve near-optimal approximation and generalization rates for multi-task operator learning, matching single-task scaling laws and performing similarly to a multi-task DeepONet extension.
citing papers explorer
-
Latent Generative Solvers for Generalizable Long-Term Physics Simulation
LGS pretrained on 2.5M trajectories across 16 systems matches deterministic baselines at one step and halves 20-step error while using far less compute and adapting to held-out higher-resolution flows.
-
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.
-
A Hybridizable Neural Time Integrator for Stable Autoregressive Forecasting
A hybrid transformer-FEM integrator provides provable discrete energy preservation and gradient bounds for stable autoregressive forecasting of chaotic systems, with 65x fewer parameters and 9000x speedup in a fusion surrogate trained on 12 simulations.
-
A Multimodal Vision Transformer-based Modeling Framework for Prediction of Fluid Flows in Energy Systems
A multimodal SwinV2-UNet vision transformer conditioned on data modality and time predicts spatiotemporal fluid flows and reconstructs unobserved fields from limited views using CFD data of argon jet injection.
-
Flow marching for a generative PDE foundation model
Flow Marching jointly samples noise and physical time to learn a velocity field for generative PDE modeling, paired with a latent autoencoder and efficient transformer for large-scale pretraining on 2.5M trajectories.
-
Multiple Neural Operators Achieve Near-Optimal Rates for Multi-Task Learning
Multiple Neural Operators achieve near-optimal approximation and generalization rates for multi-task operator learning, matching single-task scaling laws and performing similarly to a multi-task DeepONet extension.