papers

Publications (34)

cs.AI2019

Learning to Make Analogies by Contrasting Abstract Relational Structure

Felix Hill, Adam Santoro, David G. T. Barrett +2

Analogical reasoning has been a principal focus of various waves of AI research. Analogy is particularly challenging for machines because it requires relational structures to be re…

cs.CL2017

A simple neural network module for relational reasoning

Adam Santoro, David Raposo, David G. T. Barrett +4

Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation…

cs.LG2018

Relational inductive biases, deep learning, and graph networks

Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24

Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…

cs.LG2022

Intra-agent speech permits zero-shot task acquisition

Chen Yan, Federico Carnevale, Petko Georgiev +7

Human language learners are exposed to a trickle of informative, context-sensitive language, but a flood of raw sensory data. Through both social language use and internal processe…

cs.LG2021

Imitating Interactive Intelligence

Josh Abramson, Arun Ahuja, Iain Barr +26

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…

cs.AI2022

Symbolic Behaviour in Artificial Intelligence

Adam Santoro, Andrew Lampinen, Kory Mathewson +2

The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial…

cs.LG2020

Automated curricula through setter-solver interactions

Sebastien Racaniere, Andrew K. Lampinen, Adam Santoro +3

Reinforcement learning algorithms use correlations between policies and rewards to improve agent performance. But in dynamic or sparsely rewarding environments these correlations a…

cs.NE2018

Hyperbolic Attention Networks

Caglar Gulcehre, Misha Denil, Mateusz Malinowski +8

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure. A few recent app…

cs.AI2020

Environmental drivers of systematicity and generalization in a situated agent

Felix Hill, Andrew Lampinen, Rosalia Schneider +4

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here…

cs.LG2022

A data-driven approach for learning to control computers

Peter C Humphreys, David Raposo, Toby Pohlen +8

It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-sc…

cs.LG2018

Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

Sergey Bartunov, Adam Santoro, Blake A. Richards +3

The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learning and AI, however, has inspired propos…

cs.LG2022

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

DeepMind Interactive Agents Team, Josh Abramson, Arun Ahuja +22

A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through…

cs.LG2018

Relational Deep Reinforcement Learning

Vinicius Zambaldi, David Raposo, Adam Santoro +13

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through st…

cs.CV2018

Learning Visual Question Answering by Bootstrapping Hard Attention

Mateusz Malinowski, Carl Doersch, Adam Santoro +1

Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all…

cs.LG2018

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…

cs.LG2022

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

Josh Abramson, Arun Ahuja, Federico Carnevale +16

An important goal in artificial intelligence is to create agents that can both interact naturally with humans and learn from their feedback. Here we demonstrate how to use reinforc…

cs.LG2021

Rapid Task-Solving in Novel Environments

Sam Ritter, Ryan Faulkner, Laurent Sartran +3

We propose the challenge of rapid task-solving in novel environments (RTS), wherein an agent must solve a series of tasks as rapidly as possible in an unfamiliar environment. An ef…

cs.LG2018

Relational recurrent neural networks

Adam Santoro, Ryan Faulkner, David Raposo +7

Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to per…

cs.LG2016

One-shot Learning with Memory-Augmented Neural Networks

Adam Santoro, Sergey Bartunov, Matthew Botvinick +2

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-base…

cs.CL2025

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…

cs.LG2025

Tracing the Representation Geometry of Language Models from Pretraining to Post-training

Melody Zixuan Li, Kumar Krishna Agrawal, Arna Ghosh +4

Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learn…

q-bio.NC2019

Is coding a relevant metaphor for building AI? A commentary on "Is coding a relevant metaphor for the brain?", by Romain Brette

Adam Santoro, Felix Hill, David Barrett +3

Brette contends that the neural coding metaphor is an invalid basis for theories of what the brain does. Here, we argue that it is an insufficient guide for building an artificial…

stat.ML2017

Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study

Samuel Ritter, David G. T. Barrett, Adam Santoro +1

Deep neural networks (DNNs) have achieved unprecedented performance on a wide range of complex tasks, rapidly outpacing our understanding of the nature of their solutions. This has…

cs.LG2022

Tell me why! Explanations support learning relational and causal structure

Andrew K. Lampinen, Nicholas A. Roy, Ishita Dasgupta +8

Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of e…

cs.LG2019

An investigation of model-free planning

Arthur Guez, Mehdi Mirza, Karol Gregor +10

The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that…

cs.LG2017

Discovering objects and their relations from entangled scene representations

David Raposo, Adam Santoro, David Barrett +3

Our world can be succinctly and compactly described as structured scenes of objects and relations. A typical room, for example, contains salient objects such as tables, chairs and…

cs.LG2022

Data Distributional Properties Drive Emergent In-Context Learning in Transformers

Stephanie C. Y. Chan, Adam Santoro, Andrew K. Lampinen +5

Large transformer-based models are able to perform in-context few-shot learning, without being explicitly trained for it. This observation raises the question: what aspects of the…

cs.LG2022

Evaluating Multimodal Interactive Agents

Josh Abramson, Arun Ahuja, Federico Carnevale +12

Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these interactions is challenging: collecting…

cs.CL2023

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…

cs.CV2021

Attention over learned object embeddings enables complex visual reasoning

David Ding, Felix Hill, Adam Santoro +2

Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging ta…

cs.LG2018

Measuring abstract reasoning in neural networks

David G. T. Barrett, Felix Hill, Adam Santoro +2

Whether neural networks can learn abstract reasoning or whether they merely rely on superficial statistics is a topic of recent debate. Here, we propose a dataset and challenge des…

cs.LG2017

Generative Temporal Models with Memory

Mevlana Gemici, Chia-Chun Hung, Adam Santoro +5

We consider the general problem of modeling temporal data with long-range dependencies, wherein new observations are fully or partially predictable based on temporally-distant, pas…

cs.LG2024

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

David Raposo, Sam Ritter, Blake Richards +3

Transformer-based language models spread FLOPs uniformly across input sequences. In this work we demonstrate that transformers can instead learn to dynamically allocate FLOPs (or c…

cs.LG2021

Synthetic Returns for Long-Term Credit Assignment

David Raposo, Sam Ritter, Adam Santoro +5

Since the earliest days of reinforcement learning, the workhorse method for assigning credit to actions over time has been temporal-difference (TD) learning, which propagates credi…