Research

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

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

WaveNet

WaveNet creates more natural-sounding speech for products used by millions of people around the world.

Find out more

Featured publications

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

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

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

Chip text

No items found

Publication

Search-Improved Game-Theoretic Multiagent Reinforcement Learning in General and Negotiation Games

Zun Li, Marc Lanctot, Kevin McKee, Luke Marris, Ian Gemp, Daniel Hennes, Kate Larson, Yoram Bachrach, Paul Muller, Michael Wellman *

AAMAS

Download

Publication

Is forgetting less a good inductive bias for forward transfer?

Arslan Chaudhry, Jiefeng Chen, Timothy Nguyen, Dilan Gorur

ICLR

Download

Publication

Meta-Learning Black-Box Optimization via Black-Box Optimization

Robert Lange, Tom Schaul, Tom Zahavy, Yutian Chen, Valentin Dalibard, Chris Lu, Satinder Baveja, Sebastian Flennerhag

ICLR

Download

Publication

Equilibrium-Invariant Embedding, Metric Space, and Fundamental Set of 2×2 Normal-Form Games

Luke Marris, Ian Gemp, Georgios Piliouras

arXiv

Download

Publication

Fitting Autoregressive Graph Generative Models through Maximum Likelihood Estimation

Xu Han *, Xiaohui Chen *, Francisco Ruiz, Liping Liu *

JMLR

Download

Publication

Rethinking Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization

Aishwarya Agrawal, Ivana Kajic, Emanuele Bugliarello, Elnaz Davoodi, Anita Gergely, Aida Nematzadeh, Phil Blunsom *

EACL

Download

Publication

Three ways to improve feature alignment for open vocabulary detection

Relja Arandjelovic, Alex Andonian, Jean-baptiste Alayrac, Arthur Mensch, Olivier Henaff, Andrew Zisserman

arXiv

Download

Publication

Fast exploration and learning of latent graphs with aliased observations

Miguel Lazaro-Gredilla, Ishan Deshpande, Siva Swaminathan, Meet Dave, Dileep George

arXiv

Download

Publication

Evaluating Number Discrimination in Deep Neural Networks for Vision

Ivana Kajic, Aida Nematzadeh

CogSci

Download

Publication

Denoising diffusion samplers

Francisco Vargas, Will Grathwohl, Arnaud Doucet

ICLR

Download

Publication

Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains

Jingwei Zhang, Jost Tobias Springenberg, Martin Riedmiller, Nicolas Heess, Arunkumar Byravan, Leonard Hasenclever, Abbas Abdolmaleki, Dushyant Rao

arXiv

Download

Publication

Graph schemas as abstractions for transfer learning, inference, and planning

Swaroop Guntupalli, Rajkumar Vasudeva Raju, Shrinu Kushagra, Carter Wendelken, Danny Sawyer, Ishan Deshpande, Stannis Zhou, Miguel Lazaro-Gredilla, Dileep George

arXiv

Download

Publication

Universal Agent Mixtures and the Geometry of Intelligence

Samuel Allen Alexander *, David Quarel *, Len Du *, Marcus Hutter

AISTATS

Download

Publication

Scaling Goal-based Exploration via Pruning Proto-goals

Akhil Bagaria *, Ray Jiang, Ramana Kumar, Tom Schaul

arXiv

Download

Publication

Equivariant MuZero

Andreea Deac *, Theophane Weber, George Papamakarios

arXiv

Download

Publication

3D Neural Embedding Likelihood for Robust Sim-to-Real Transfer in Inverse Graphics

Stannis Zhou, Nishad Gothoskar *, Lirui Wang *, Josh Tenenbaum *, Dan Gutfreund *, Miguel Lazaro-Gredilla, Dileep George, Vikash Mansinghka *

arXiv

Download

Publication

Exploration via Epistemic Value Estimation

Simon Schmitt, John Shawe-Taylor *, Hado van Hasselt

AAAI

Download

Publication

Diversity Through Exclusion (DTE): Niche Identification for Reinforcement Learning through Value-Decomposition

Peter Sunehag, Joel Leibo, Sasha Vezhnevets, Igor Mordatch *, Edgar Duéñez-Guzmán

AAMAS

Download

Publication

Reinforcement Learning for Minimizing Age of Information over Wireless Links

Elif Tugce Ceran *, Deniz Gündüz *, Andras Gyorgy

Age of Information: Foundations and Applications

Download

Publication

PGMax: Factor Graphs for Discrete Probabilistic Graphical Models and Loopy Belief Propagation in JAX

Stannis Zhou, Antoine Dedieu, Nishanth Kumar *, Wolfgang Lehrach, Miguel Lazaro-Gredilla, Shrinu Kushagra, Dileep George

arXiv

Download

Publication

Learning Noisy OR Bayesian Networks with Max-Product Belief Propagation

Antoine Dedieu, Stannis Zhou, Dileep George, Miguel Lazaro-Gredilla

arXiv

Download

Publication

Dual Algorithmic Reasoning

Danilo Numeroso *, Davide Bacciu *, Petar Veličković

ICLR

Download

Publication

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta, Theodore Sumers *

arXiv

Download

Publication

Pragmatic Fairness: Developing Policies with Outcome Disparity Control

Silvia Chiappa, Alan Malek, Ricardo Silva *, Siyuan Guo *

arXiv

Download

Publication

On a continuous time model of gradient descent dynamics and instability in deep learning

Mihaela Rosca, Yan Wu, Chongli Qin, Benoit Dherin *

Transactions on Machine Learning Research (TMLR)

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

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

Highlighted research

Featured publications

Publications

Accelerating research with tools, platforms, and environments

Pioneering intelligent systems, with scientific rigour