6 papers
Learnable composition for neural operators
Zituo Chen, Baiming Zhang, Sili Deng
Neural operators are fast, differentiable surrogates for physical simulation, but their accuracy often degrades when domain geometry, size, or operating conditions differ from trai…
Neural operator discovery from heterogeneous trajectories
Zituo Chen, Qiaofeng Li, Jiaxin Hu +1
Neural operators provide data-driven mappings for modeling dynamical systems. Extending them to families of systems typically requires explicit conditioning variables such as physi…
3-D Representations for Hyperspectral Flame Tomography
Nicolas Tricard, Zituo Chen, Sili Deng
Flame tomography is a compelling approach for extracting large amounts of data from experiments via 3-D thermochemical reconstruction. Recent efforts employing neural-network flame…
GLU: Global-Local-Uncertainty Fusion for Scalable Spatiotemporal Reconstruction and Forecasting
Linzheng Wang, Jason Chen, Nicolas Tricard +2
Digital twins of complex physical systems are expected to infer unobserved states from sparse measurements and predict their evolution in time, yet these two functions are typicall…
Latent Generative Solvers for Generalizable Long-Term Physics Simulation
Zituo Chen, Sili Deng
Reliable physics simulation demands two capabilities that today's neural PDE solvers do not deliver together: generalization across heterogeneous PDE families, and stability under…
Flow marching for a generative PDE foundation model
Zituo Chen, Sili Deng
Pretraining on large-scale collections of PDE-governed spatiotemporal trajectories has recently shown promise for building generalizable models of dynamical systems. Yet most exist…