JAX, M.D.: A Framework for Differentiable Physics. Samuel S. Schoenholz, Ekin D. Cubuk. NeurIPS 2020.

arxiv.orgsite

Introduces JAX, M.D., a differentiable physics library which includes simulation environments, interaction potentials, neural networks, and more.

from

JAX

added

2026-10-10

likes

0

similar

1. ▲
   JaxDF github.com

   tool category #jax link ↗

   Framework for differentiable simulators with arbitrary discretizations.

   
2. ▲
   JAX, M.D. github.com

   tool category #jax link ↗

   Accelerated, differential molecular dynamics.

   
3. ▲
   BRAX github.com

   tool category #jax link ↗

   Differentiable physics engine to simulate environments along with learning algorithms to train agents for these environments.

   
4. ▲
   Jax in Action manning.com

   site category #jax link ↗

   A hands-on guide to using JAX for deep learning and other mathematically-intensive applications.

5. ▲
   dynamiqs github.com

   tool category #jax link ↗

   High-performance and differentiable simulations of quantum systems with JAX.

   
6. ▲
   JAXopt github.com

   tool category #jax link ↗

   Hardware accelerated (GPU/TPU), batchable and differentiable optimizers in JAX.

   

JAX › Papers: “Introduces JAX, M.D., a differentiable physics library which includes simulation environments, interaction potentials, neural networks, and more.”