JAX-MPM: A Learning-Augmented Differentiable Meshfree Framework for GPU-Accelerated Lagrangian Simulation and Geophysical Inverse Modeling
cs.LG
Submitted: 2025-07-06
Updated: 2025-09-27
Code: https://github.com/ax-ml/jax
Terminology
Sources
- The Elements of Differentiable Programming
- DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physics
- Differentiable graph neural network simulator for forward and inverse modeling of multi-layered slope system with multiple material properties
- DiffTaichi: Differentiable Programming for Physical Simulation
- A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
- Scalable and modular material point method for large-scale simulations
- PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification
- Fourier Neural Operator for Parametric Partial Differential Equations
- Universal Differential Equations for Scientific Machine Learning
- Differentiable Programming for Differential Equations: A Review
- JAX-SPH: A Differentiable Smoothed Particle Hydrodynamics Framework
- An End-to-End Differentiable Framework for Contact-Aware Robot Design
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis