نسخة أولية وصول مفتوح
Transolver-$σ$: Joint Spectral-Physical Subspace Modeling for Neural PDE Solving
Neural solvers offer efficient surrogates for numerical simulation of partial differential equations (PDEs). For time-dependent problems, strong one-step accuracy does not necessarily translate into reliable autoregressive rollout. We observe that a solver based only on physical-state modeling can achieve lower one-ste …