Research
Publications
Open source
Highlighted Research
AlphaFold
AlphaGo
WaveNet
Blog
Applied
Company
Ethics and Society
Events
Life at DeepMind
Open source
Research
Technical blog
About
Impact
Safety & Ethics
Careers
Education
Learning resources
The Podcast
Press
Terms and conditions
Privacy policy
Vulnerability disclosure
Modern Slavery Statement
Alphabet Inc.

We work on some of the most complex and interesting challenges in AI.

Explore our research across
Deep learning
Theory and foundations
Control and robotics
Unsupervised learning and generative models
Reinforcement learning
Neuroscience
Sciences

Highlighted research

View all highlighted research
Visual representation of AlphaFold.
AlphaFold
AlphaFold can accurately predict 3D models of protein structures and has the potential to accelerate research in every field of biology.
Find out more
Visual representation of WaveNet generating system voices on devices.
WaveNet
WaveNet creates more natural-sounding speech for products used by millions of people around the world.
Find out more

Featured publications

Visual representation of AlphaFold.
Restoring and attributing ancient texts using deep neural networks
Restoring, placing, and dating ancient texts through collaboration between AI and historians.
Nature
View publication
View blog post
Visual representation of WaveNet generating system voices on devices.
Magnetic control of tokamak plasmas through deep reinforcement learning
Successfully controlling the nuclear fusion plasma in a tokamak with deep reinforcement learning.
Nature
View publication
View blog post
Visual representation of WaveNet generating system voices on devices.
Advancing mathematics by guiding human intuition with AI
Applying AI toward discovering new insights in two areas of pure mathematics: topology and representation theory.
Nature
View publication
View blog post

Publications

Tags
Venues
Reset
Chip text
No items found
Paper
Publication
Discovering Quantum Phase Transitions with Fermionic Neural Networks
Gino Cassella *, Halvard Sutterud *, Matthew Foulkes *, David Pfau, Neil Drummond *, Sam Azadi *, James Spencer
Physical Review Letters
Download
Paper
Publication
Transformer Grammars: Augmenting Transformer Language Models with a Syntactic Inductive Bias
Laurent Sartran, Samuel Barrett *, Adhi Kuncoro, Miloš Stanojević, Phil Blunsom *, Chris Dyer
Transactions of the Association for Computational Linguistics (TACL)
Download
Paper
Publication
An empirical study of implicit regularization in deep offline RL
Caglar Gulcehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Matt Hoffman, Mehrdad Farajtabar, Razvan Pascanu, Arnaud Doucet
Transactions on Machine Learning Research (TMLR)
Download
Paper
Publication
Confident Approximate Policy Iteration for Efficient Local Planning in q^π-realizable MDPs
Andras Gyorgy, Csaba Szepesvari, Tadashi Kozuno *, Gellért Weisz
NeurIPS
Download
Paper
Publication
Particle-Based Score Estimation for Jointly Learning Transition and Observation Models in Autonomous Driving
Angad Singh *, Omar Makhlouf *, Maximilian Igl *, Joao Messias *, Arnaud Doucet, Shimon Whiteson *
CoRL
Download
Paper
Publication
ipie: A Python-based Auxiliary-Field Quantum Monte Carlo Program with Flexibility and Efficiency on CPUs and GPUs
Fionn Malone *, Ankit Mahajan *, James Spencer, Joonho Lee *
Journal of Chemical Theory and Computation
Download
Paper
Publication
Score-based generative models learn manifold-like structures with constrained mixing
Kevin Li, Ben Moran
NeurIPS Workshop
Download
Paper
Publication
Continuous Neural Algorithmic Planners
Yu He *, Petar Veličković, Pietro Liò *, Andreea-Ioana Deac
LoG
Download
Paper
Publication
Unbiased and Efficient Sampling of Dependency Trees
Miloš Stanojević
EMNLP
Download
Paper
Publication
Reasoning-Modulated Representations
Petar Veličković, Matko Bošnjak, Thomas Kipf *, Alexander Lerchner, Raia Hadsell, Razvan Pascanu, Charles Blundell
LoG
Download
Paper
Publication
BLaDE: Robust Exploration via Diffusion Models
Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Shantanu Thakoor
Deep RL Workshop NeurIPS
Download
Paper
Publication
Learning Graph Search Heuristics
Michal Pándy *, Weikang Qiu *, Gabriele Corso *, Petar Veličković, Rex Ying *, Jure Leskovec *, Pietro Liò *
LoG
Download
Paper
Publication
Learnable Commutative Monoids for Graph Neural Networks
Euan Ong *, Petar Veličković
LoG
Download
Paper
Publication
A Generalist Neural Algorithmic Learner
Borja Ibarz, Vitaly Kurin, George Papamakarios, Kyriacos Nikiforou, Mehdi Bennani, Róbert Csordás, Andrew Dudzik, Matko Bošnjak, Alex Vitvitskyi, Yulia Rubanova, Andreea-Ioana Deac, Beatrice Bevilacqua, Yaroslav Ganin, Charles Blundell, Petar Veličković
LoG
Download
Paper
Publication
Expander Graph Propagation
Andreea-Ioana Deac, Marc Lackenby *, Petar Veličković
LoG
Download
Paper
Publication
Scaffolding cooperation in human groups with deep reinforcement learning
Kevin McKee, Andrea Tacchetti, Michiel Bakker, Jan Balaguer, Lucy Campbell-Gillingham, Richard Everett, Matt Botvinick
PsyArXiv
Download
Paper
Publication
Re-assessing Commonsense Knowledge in Large Language Models
Xiang Lorraine Li *, Adhi Kuncoro, Aida Nematzadeh, Phil Blunsom, Cyprien de Masson d'Autume, Jordan Hoffmann
EMNLP
Download
Paper
Publication
Learning rigid dynamics with face interaction graph networks
Kelsey Allen, Yulia Rubanova, Tatiana Guevara, Will Whitney, Alvaro Sanchez, Peter Battaglia, Tobias Pfaff
arXiv
Download
Paper
Publication
Learning rigid dynamics with face interaction graph networks
Kelsey Allen, Yulia Rubanova, Tatiana Guevara, Will Whitney, Alvaro Sanchez, Peter Battaglia, Tobias Pfaff
arXiv
Download
Paper
Publication
Negotiation and honesty in artificial intelligence methods for the board game of Diplomacy
János Kramár, Tom Eccles, Ian Gemp, Andrea Tacchetti, Kevin McKee, Mateusz Malinowski, Thore Graepel *, Yoram Bachrach
Nature Communications
Download
Paper
Publication
Large-Scale Retrieval for Reinforcement Learning
Peter Humphreys, Arthur Guez, Olivier Tieleman, Laurent Sifre, Theophane Weber, Timothy Lillicrap
NeurIPS
Download
Paper
Publication
A Fourier Approach to Mixture Learning
Manzil Zaheer, Guru Guruganesh *, Ankit Singh Rawat *, Mingda Qiao *, Avinava Dubey *
NeurIPS
Download
Paper
Publication
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models
Maribeth Rauh, John Mellor, Jonathan Uesato, Po-Sen Huang, Johannes Welbl, Laura Weidinger, Sumanth Dathathri, Mia Glaese, Geoffrey Irving, Iason Gabriel, William Isaac, Lisa Anne Hendricks
NeurIPS Datasets and Benchmarks Track
Download
Paper
Publication
Learning to Navigate Wikipedia by Taking Random Walks
Manzil Zaheer, Kenneth Marino, Will Grathwohl, John Schultz, Wendy Shang, Arun Ahuja, Ishita Dasgupta, Christine Kaeser-Chen, Rob Fergus
NeurIPS
Download
Paper
Publication
Turbocharging Solution Concepts: Solving NEs, CEs and CCEs with Deep Equilibrium Networks
Luke Marris, Ian Gemp, Thomas Anthony, Andrea Tacchetti, Siqi Liu, Karl Tuyls
NeurIPS
Download

Accelerating research with tools, platforms, and environments

View open source
Visual representation of control and robotics.
Visual representation of solving intelligence.

Pioneering intelligent systems, with scientific rigour

Find out about our Research team