Search papers, labs, and topics across Lattice.
School of Mechanics and Engineering Science, Peking University, Beijing, China
3
0
3
Capturing fine-scale physical structures in PDE predictions is now achievable with a novel function-projection approach that outperforms traditional methods.
Target-aligned input reparameterization slashes prediction errors for thermodynamic properties in supercritical combustion by up to 14.5 times, revolutionizing neural network efficiency.
Solving Poisson equations just got faster and more stable: NPSolver trains neural operators without solution labels by iteratively refining predictions with preconditioned conjugate gradient steps.
