#flax

Generative modeling for JAX/Flax NNX: VAEs, GANs, DDPM/DDIM/score/DiT/latent diffusion, normalizing flows, energy-based, autoregressive and geometric (SE(3), protein, point cloud, mesh) models; image, text, audio, molecular, protein, tabular and time-series modalities; a shared Trainer with callbacks and extensions; evaluation through calibrax.

JAX/Flax NNX training infrastructure: device meshes and SPMD sharding, an Orbax checkpoint store, early stopping and callbacks, W&B and MLflow logging.

...the little C# ECS that loves you back! 🦊

JAX-native differentiable protein folding framework integrating experimental NMR constraints (RDCs) and biophysical "self-correction." Several Jupyter Notebooks visualize the concepts.