Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)

[TKDE 2022] The official PyTorch implementation of the paper "Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs".

Code for: "Neural Controlled Differential Equations for Online Prediction Tasks"

Neural Ordinary Differential Equations for Reinforcement Learning

This repo is the official implementation for the series of works on (Path-dependent) Neural Jump ODEs.

Official repository for the paper "Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules" (NeurIPS 2022)

Python tools for non-intrusive reduced order modeling

🏍️ - JAX-based framework to model biological systems

Accompanying code for the paper "Amortized reparametrization: efficient and scalable variational inference for latent SDEs

Implementation of "FLOWING 🌊: Implicit Neural Flows for Structure-Preserving Morphing", to appear on NeurIPS 2025

On the forward invariance of Neural ODEs: performance guarantees for policy learning

Building, simulating, and training systems biology models using JAX/Diffrax

PINEURODEs is a repository collecting CMS group research work on the application of neural (stochastic/ordinary) differential equations and physically-informed neural networks to model complex multiscale systems.

Neural ODEs and Conditional Normalizing Flows for Generative Modeling

Benchmarks Physics-Informed Neural ODEs vs. Fine-Tuned Foundation Models (Chronos) on Cenozoic fossil data. Includes a Random Forest analysis of the Lilliput Effect to test climate vs. taphonomy drivers. Results show Neural ODEs outperform generic Transformers (MSE 13.05) in reconstructing deep-time evolutionary history.

Lagrangian and Hamiltonian Neural Ordinary Differential Equations (NODEs)

Adversarial flow matching for Bayesian neural ODEs with low-rank parameterization and uncertainty-aware continuous dynamics.

An implementation of Neural ODEs in PyTorch.

Alternative method of time-discretization for Neural ODEs

Repository of my Master Thesis Project at TUM at the end of my Ecole Polytechnique's studies. It tackles the subject of "Continuous Motion Interpolation with Neural Differential Equations"