Adaptive Runge-Kutta Dynamics
Adaptive Runge-Kutta Dynamics
Auto-generated stub. Edit this file to add more details.
A neural network integration method that employs an adaptive second-order Runge-Kutta solver to explicitly model physical state transitions in spatiotemporal dynamics.
Why It Matters
It shifts the paradigm from fixed-step neural integration to adaptive solving, providing a more robust architectural primitive for physics-informed spatiotemporal modeling.
Evidence
we introduce a physical-guided neural network, which utilizes an adaptive second-order Runge-Kutta method with physical constraints to model the physical states more precisely.
Related Papers
Metadata & Links
- created_at
- 2026-04-24T05:51:00Z