Modern 3D computer graphics technologies are able to reproduce the dynamics and
appearance of real-world environments and phenomena, building on theoretical models in …

While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

We present a data-driven approach for forecasting global weather using graph neural
networks. The system learns to step forward the current 3D atmospheric state by six hours …

Structured state space sequence (S4) models have recently achieved state-of-the-art
performance on long-range sequence modeling tasks. These models also have fast …

Foundation models have shown impressive adaptation and scalability in supervised and self-
supervised learning problems, but so far these successes have not fully translated to …

Tremendous progress has been made in reinforcement learning (RL) over the past decade.
Most of these advancements came through the continual development of new algorithms …

Recent advances in data science are impacting the development of classical force fields.
Here we review some ideas and techniques from data science that have been used in force …

The deep learning revolution has greatly been accelerated by the'hardware lottery': Recent
advances in modern hardware accelerators, compilers and the availability of open-source …

Optimization is a ubiquitous modeling tool and is often deployed in settings which
repeatedly solve similar instances of the same problem. Amortized optimization methods …

We explore a data-driven approach for learning to optimize neural networks. We construct a
dataset of neural network checkpoints and train a generative model on the parameters. In …