A Julia package for inverse problems in optics with differentiable forward models.

A minimal implementation of diffusion models for text generation

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Code for Neural Spline Flows paper

Academic presentations with Slidev made simple 🎓

Normalizing flows in PyTorch

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Overleaf Two-Way Synchronization

Synthetic data curation for post-training and structured data extraction

A generative world for general-purpose robotics & embodied AI learning.

For optimization algorithm research and development.

Python implementation of soft-DTW.

Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.

physics-informed neural network for elastodynamics problem

TorchDR - PyTorch Dimensionality Reduction

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Investigating PINNs

A differentiable PDE solving framework for machine learning

Physics-informed learning of governing equations from scarce data

PDEBench: An Extensive Benchmark for Scientific Machine Learning

A benchmark for the next generation of data-driven global weather models.

Aligning protein generative models with experimental fitness

Easy generative modeling in PyTorch

pyOptSparse is an object-oriented framework for formulating and solving nonlinear constrained optimization problems in an efficient, reusable, and portable manner.