Publications (18)
Unifying Count-Based Exploration and Intrinsic Motivation
Marc G. Bellemare, Sriram Srinivasan, Georg Ostrovski +3
We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration…
The number of -free graphs
Robert Morris, David Saxton
One of the most basic questions one can ask about a graph is: how many -free graphs on vertices are there? For non-bipartite , the answer to this question has been we…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
An asymmetric container lemma and the structure of graphs with no induced -cycle
Robert Morris, Wojciech Samotij, David Saxton
The method of hypergraph containers, introduced recently by Balogh, Morris, and Samotij, and independently by Saxton and Thomason, has proved to be an extremely useful tool in the…
Supersaturation for hereditary properties
David Saxton
Let be a collection of -uniform hypergraphs, and let . It is known that there exists such that the probability of a random -gr…
Analysing Mathematical Reasoning Abilities of Neural Models
David Saxton, Edward Grefenstette, Felix Hill +1
Mathematical reasoning---a core ability within human intelligence---presents some unique challenges as a domain: we do not come to understand and solve mathematical problems primar…
Can Neural Networks Understand Logical Entailment?
Richard Evans, David Saxton, David Amos +2
We introduce a new dataset of logical entailments for the purpose of measuring models' ability to capture and exploit the structure of logical expressions against an entailment pre…
Online containers for hypergraphs, with applications to linear equations
David Saxton, Andrew Thomason
A set of containers for a hypergraph G is a collection of vertex subsets, such that for every independent (or, indeed, merely sparse) set in G there is some subset in the collectio…
Strictly monotonic multidimensional sequences and stable sets in pillage games
David Saxton
Let have size . We show that there are distinct points such that for each , the coordina…
Conditional Neural Processes
Marta Garnelo, Dan Rosenbaum, Chris J. Maddison +6
Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function. On the other hand, Bayesian methods, such as Gaussian Proce…
Programmable Agents
Misha Denil, Sergio Gómez Colmenarejo, Serkan Cabi +2
We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generali…
De novo design of high-affinity protein binders with AlphaProteo
Vinicius Zambaldi, David La, Alexander E. Chu +29
Computational design of protein-binding proteins is a fundamental capability with broad utility in biomedical research and biotechnology. Recent methods have made strides against s…
On the Ramsey number of the triangle and the cube
Gonzalo Fiz Pontiveros, Simon Griffiths, Robert Morris +2
The Ramsey number r(K_3,Q_n) is the smallest integer N such that every red-blue colouring of the edges of the complete graph K_N contains either a red n-dimensional hypercube, or a…
Meta-Learning surrogate models for sequential decision making
Alexandre Galashov, Jonathan Schwarz, Hyunjik Kim +5
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning.…
Unsupervised Predictive Memory in a Goal-Directed Agent
Greg Wayne, Chia-Chun Hung, David Amos +21
Animals execute goal-directed behaviours despite the limited range and scope of their sensors. To cope, they explore environments and store memories maintaining estimates of import…
The Ramsey number of the clique and the hypercube
Gonzalo Fiz Pontiveros, Simon Griffiths, Robert Morris +2
The Ramsey number r(K_s,Q_n) is the smallest positive integer N such that every red-blue colouring of the edges of the complete graph K_N on N vertices contains either a red n-dime…
Simple containers for simple hypergraphs
David Saxton, Andrew Thomason
We give an easy method for constructing containers for simple hypergraphs. Some applications are given; in particular, a very transparent calculation is offered for the number of H…
Hypergraph containers
David Saxton, Andrew Thomason
We develop a notion of containment for independent sets in hypergraphs. For every -uniform hypergraph , we find a relatively small collection of vertex subsets, such that…