Predict dynamic behaviors in a physics system in a way that's computationally efficient and adaptable to a range of scenarios.

On a sunny day, Alyx Albuquerque’s boundless joy is infectious. She bounces up from her computer at her design studio, ...

In this paper, a data-driven evolutionary algorithm based on inductive graph neural networks (DEA-IGNN) is proposed to solve MMOPs ... which uses the traditional variation operators to generate ...

Abstract: In autonomous driving environments, generative adversarial networks (GANs) are often used to predict the future trajectories ... Second, multifaceted aspects, including energy consumption, ...

A library for solving differential equations using neural networks based on PyTorch, used by multiple research groups around the world, including at Harvard IACS.