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

Explore our research across
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
Tags
Venues
No items found
Paper
Publication
Constrained Offline RL via Stationary Distribution Correction Estimation
Paper
Publication
Semi-analytical Industrial Cooling System Model for Reinforcement Learning
Paper
Publication
Generalised Policy Improvement with Geometric Policy Composition
Paper
Publication
From Dirichlet to Rubin: Optimistic exploration in RL without bonuses
Paper
Publication
Towards Coherent and Consistent Use of Entities in Narrative Generation
Paper
Publication
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Paper
Publication
Importance Weighting Approach in Kernel Bayes' Rule
Paper
Publication
Intuitive physics learning in a deep-learning model inspired by developmental psychology
Paper
Publication
Human-centred mechanism design with Democratic AI
Paper
Publication
Scaling Gaussian process optimization by evaluating a few unique candidates multiple times
Paper
Publication
Input-level Inductive Biases for 3D Reconstruction
Paper
Publication
Subverting machines, fluctuating identities: Re-learning human categorization
Paper
Publication
BYOL-Explore: Exploration with Bootstrapped Prediction
Paper
Publication
Unlocking High-Accuracy Differentially Private Image Classification through Scale
Paper
Publication
Sheaf Neural Networks with Connection Laplacians
Paper
Publication
Perceiver AR: general-purpose, long-context autoregressive generation
Paper
Publication
Simplex Neural Population Learning: Any-Mixture Bayes-Optimality in Symmetric Zero-sum Games
Paper
Publication
An EigenGame for the Generalized Eigenvalue Problem
Paper
Publication
Utility of Equivariant Message Passing in Cortical Mesh Segmentation
Paper
Publication
StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models
Paper
Publication
The CLRS Algorithmic Reasoning Benchmark
Paper
Publication
The CLRS Algorithmic Reasoning Benchmark
Paper
Publication
Tell me why! Explanations support learning relational and causal structure
Paper
Publication
Objective Robustness in Deep Reinforcement Learning
Paper
Publication
Evaluating Multimodal Interactive Agents