CraftSPH: A high-accuracy and composable differentiable SPH solver implemented in PyTorch
physics.flu-dyn, cs.LG, cs.NA, math.NA
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/GenMNL/CraftSPH
Terminology
Sources
- DiffTaichi: Differentiable Programming for Physical Simulation
- JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework
Related papers
- Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
- Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
- Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
- Diffraction of walking drops by a standing Faraday wave
- Linear causality and stability constraints on relativistic second-order magnetohydrodynamics
- Adjoint-based shape optimization of a ship hull using a Conditional Variational Autoencoder (CVAE) assisted propulsion surrogate model