TORAX: Tokamak transport simulation in JAX

An interactive dashboard for visualisation, integration and classification of data using Active Learning.

An Automized Partial Differential Equation solver based on JAX

Interpolation and function approximation with JAX

A Warp Drive for Neural PDE Solvers

Official implementation of the paper "Towards a Certificate of Trust: Task-Aware OOD Detection for Scientific AI"

Code repository for "Learned Turbulence Modelling with Differentiable Fluid Solvers"

[NeurIPS 2025] Official PyTorch implementation of the CALM layers and CALM-PDE model.

Deep-learning framework for Engineering AI. Built on transformer building blocks, it delivers the full engineering stack, allowing teams to build, train, and operate industrial simulation models ac…

Pinneaple is an open-source Physics AI toolkit for Physics-Informed Neural Networks (PINNs), scientific ML, geometry processing, solvers, and reproducible training pipelines.

Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.

A differentiable cosmology library in JAX

This repository containts materials for End-to-End AI for Science

[ICLR26 Oral] RealPDEBench: A Benchmark for Complex Physical Systems with Paired Real-World and Simulated Data

Information hub for our project training the largest possible historical LLMs.

Differentiable Fluid Dynamics Package

Agustinus' very opiniated publication-ready plotting library

Unstructured Compressible Navier Stokes 3D code (UCNS3D)

NeurIPS-2025

"Paper2Slides: From Paper to Presentation in One Click"

Coordinate Axes for JAX

Implementation of Diffusion Transformer (DiT) in JAX

Multi-Agent (Crafter + NetHack) in JAX

JAX compatible datetime and timedelta types

Official implementation of the NeurIPS 2025 spotlight paper "Light-Weight Diffusion Multiplier and Uncertainty Quantification for Fourier Neural Operators"

VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction