Tag
提出 Invariant-Conditioned Isotropic Kernel Neural Operator (IKNO)，通过仅依赖旋转不变标量与随数据旋转的方向构建局部交互，在三维 Navier–Stokes 动力学上实现数值精度级别的 SO(3) 等变性，同时参数量比 Tensor Field Network 少 5.6 倍。
This paper introduces ADSL-PDE, a domain-specific language that provides a structured search space for auto-designing neural PDE solvers, improving search efficiency and optimization stability by abstracting away low-level implementation details. The evolutionary agent built on this representation achieves over 52% performance improvement within the first ten iterations across PDE benchmarks.
This paper introduces breakeven complexity, a metric to determine when neural PDE solvers become cost-effective compared to traditional numerical solvers. The framework uses scaling laws to allocate training budgets and evaluates multiple neural solvers on diverse PDE benchmarks.