Peter Battaglia

research

∙ 09/05/2023

Diffusion Generative Inverse Design

Inverse design refers to the problem of optimizing the input of an objec...

0 Marin Vlastelica, et al. ∙

research

∙ 08/29/2023

WeatherBench 2: A benchmark for the next generation of data-driven global weather models

WeatherBench 2 is an update to the global, medium-range (1-14 day) weath...

0 Stephan Rasp, et al. ∙

research

∙ 12/24/2022

GraphCast: Learning skillful medium-range global weather forecasting

We introduce a machine-learning (ML)-based weather simulator–called "Gra...

0 Remi Lam, et al. ∙

research

∙ 12/07/2022

Learning rigid dynamics with face interaction graph networks

Simulating rigid collisions among arbitrary shapes is notoriously diffic...

0 Kelsey R. Allen, et al. ∙

research

∙ 10/02/2022

MultiScale MeshGraphNets

In recent years, there has been a growing interest in using machine lear...

0 Meire Fortunato, et al. ∙

research

∙ 05/31/2022

Pre-training via Denoising for Molecular Property Prediction

Many important problems involving molecular property prediction from 3D ...

0 Sheheryar Zaidi, et al. ∙

research

∙ 03/17/2022

Transframer: Arbitrary Frame Prediction with Generative Models

We present a general-purpose framework for image modelling and vision ta...

0 Charlie Nash, et al. ∙

research

∙ 02/04/2022

Rediscovering orbital mechanics with machine learning

We present an approach for using machine learning to automatically disco...

0 Pablo Lemos, et al. ∙

research

∙ 02/01/2022

Physical Design using Differentiable Learned Simulators

Designing physical artifacts that serve a purpose - such as tools and ot...

0 Kelsey R. Allen, et al. ∙

research

∙ 12/31/2021

Learned Coarse Models for Efficient Turbulence Simulation

Turbulence simulation with classical numerical solvers requires very hig...

5 Kimberly Stachenfeld, et al. ∙

research

∙ 12/16/2021

Constraint-based graph network simulator

In the rapidly advancing area of learned physical simulators, nearly all...

0 Yulia Rubanova, et al. ∙

research

∙ 10/12/2021

Learning ground states of quantum Hamiltonians with graph networks

Solving for the lowest energy eigenstate of the many-body Schrodinger eq...

0 Dmitrii Kochkov, et al. ∙

research

∙ 06/15/2021

Very Deep Graph Neural Networks Via Noise Regularisation

Graph Neural Networks (GNNs) perform learned message passing over an inp...

0 Jonathan Godwin, et al. ∙

research

∙ 01/11/2021

A Bayesian neural network predicts the dissolution of compact planetary systems

Despite over three hundred years of effort, no solutions exist for predi...

270 Miles Cranmer, et al. ∙

research

∙ 12/31/2020

Graph Networks with Spectral Message Passing

Graph Neural Networks (GNNs) are the subject of intense focus by the mac...

0 Kimberly Stachenfeld, et al. ∙

research

∙ 06/19/2020

Discovering Symbolic Models from Deep Learning with Inductive Biases

We develop a general approach to distill symbolic representations of a l...

12 Miles Cranmer, et al. ∙

research

∙ 03/10/2020

Lagrangian Neural Networks

Accurate models of the world are built upon notions of its underlying sy...

9 Miles Cranmer, et al. ∙

research

∙ 09/27/2019

Hamiltonian Graph Networks with ODE Integrators

We introduce an approach for imposing physically informed inductive bias...

0 Alvaro Sanchez-Gonzalez, et al. ∙

research

∙ 09/12/2019

Learning Symbolic Physics with Graph Networks

We introduce an approach for imposing physically motivated inductive bia...

0 Miles D. Cranmer, et al. ∙

research

∙ 01/23/2019

Causal Reasoning from Meta-reinforcement Learning

Discovering and exploiting the causal structure in the environment is a ...

0 Ishita Dasgupta, et al. ∙

research

∙ 12/04/2018

Compositional Imitation Learning: Explaining and executing one task at a time

We introduce a framework for Compositional Imitation Learning and Execut...

4 Thomas Kipf, et al. ∙

research

∙ 09/05/2018

Modeling human intuitions about liquid flow with particle-based simulation

Humans can easily describe, imagine, and, crucially, predict a wide vari...

0 Christopher J. Bates, et al. ∙

research

∙ 08/01/2018

Learning Visual Question Answering by Bootstrapping Hard Attention

Attention mechanisms in biological perception are thought to select subs...

6 Mateusz Malinowski, et al. ∙

research

∙ 06/05/2018

Relational Deep Reinforcement Learning

We introduce an approach for deep reinforcement learning (RL) that impro...

0 Vinicius Zambaldi, et al. ∙

research

∙ 06/04/2018

Graph networks as learnable physics engines for inference and control

Understanding and interacting with everyday physical scenes requires ric...

2 Alvaro Sanchez-Gonzalez, et al. ∙

research

∙ 05/24/2018

Hyperbolic Attention Networks

We introduce hyperbolic attention networks to endow neural networks with...

0 Caglar Gulcehre, et al. ∙

research

∙ 03/08/2018

Learning Deep Generative Models of Graphs

Graphs are fundamental data structures which concisely capture the relat...

0 Yujia Li, et al. ∙

research

∙ 07/19/2017

Imagination-Augmented Agents for Deep Reinforcement Learning

We introduce Imagination-Augmented Agents (I2As), a novel architecture f...

0 Theophane Weber, et al. ∙

research

∙ 07/19/2017

Learning model-based planning from scratch

Conventional wisdom holds that model-based planning is a powerful approa...

0 Razvan Pascanu, et al. ∙

research

∙ 06/05/2017

Visual Interaction Networks

From just a glance, humans can make rich predictions about the future st...

0 Nicholas Watters, et al. ∙

research

∙ 06/05/2017

A simple neural network module for relational reasoning

Relational reasoning is a central component of generally intelligent beh...

0 Adam Santoro, et al. ∙

research

∙ 11/06/2016

Learning to Perform Physics Experiments via Deep Reinforcement Learning

When encountering novel objects, humans are able to infer a wide range o...

0 Misha Denil, et al. ∙

research

∙ 07/03/2016

Unsupervised Learning of 3D Structure from Images

A key goal of computer vision is to recover the underlying 3D structure ...

0 Danilo Jimenez Rezende, et al. ∙

Peter Battaglia

Featured Co-authors