b'Felix Hill'

research

∙ 03/13/2023

Vision-Language Models as Success Detectors

Detecting successful behaviour is crucial for training intelligent agent...

7 Yuqing Du, et al. ∙

research

∙ 02/09/2023

The Edge of Orthogonality: A Simple View of What Makes BYOL Tick

Self-predictive unsupervised learning methods such as BYOL or SimSiam ha...

0 Pierre H. Richemond, et al. ∙

research

∙ 02/01/2023

Collaborating with language models for embodied reasoning

Reasoning in a complex and ambiguous environment is a key goal for Reinf...

0 Ishita Dasgupta, et al. ∙

research

∙ 01/12/2023

SemPPL: Predicting pseudo-labels for better contrastive representations

Learning from large amounts of unsupervised data and a small amount of s...

0 Matko Bošnjak, et al. ∙

research

∙ 10/11/2022

Transformers generalize differently from information stored in context vs in weights

Transformer models can use two fundamentally different kinds of informat...

0 Stephanie C. Y. Chan, et al. ∙

research

∙ 08/05/2022

Meaning without reference in large language models

The widespread success of large language models (LLMs) has been met with...

1 Steven T. Piantadosi, et al. ∙

research

∙ 07/14/2022

Language models show human-like content effects on reasoning

Abstract reasoning is a key ability for an intelligent system. Large lan...

9 Ishita Dasgupta, et al. ∙

research

∙ 06/16/2022

Know your audience: specializing grounded language models with the game of Dixit

Effective communication requires adapting to the idiosyncratic common gr...

0 Aaditya K. Singh, et al. ∙

research

∙ 04/08/2022

Semantic Exploration from Language Abstractions and Pretrained Representations

Continuous first-person 3D environments pose unique exploration challeng...

0 Allison C. Tam, et al. ∙

research

∙ 04/05/2022

Can language models learn from explanations in context?

Large language models can perform new tasks by adapting to a few in-cont...

2 Andrew K. Lampinen, et al. ∙

research

∙ 03/15/2022

Zipfian environments for Reinforcement Learning

As humans and animals learn in the natural world, they encounter distrib...

0 Stephanie C. Y. Chan, et al. ∙

research

∙ 12/15/2021

Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning

Deep reinforcement learning (Deep RL) has recently seen significant prog...

11 Wilka Carvalho, et al. ∙

research

∙ 12/07/2021

Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning

A common vision from science fiction is that robots will one day inhabit...

1 DeepMind Interactive Agents Team, et al. ∙

research

∙ 12/07/2021

Tell me why! – Explanations support learning of relational and causal structure

Explanations play a considerable role in human learning, especially in a...

12 Andrew K. Lampinen, et al. ∙

research

∙ 10/18/2021

BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation

Natural language processing (NLP) systems are increasingly trained to ge...

7 Thomas Scialom, et al. ∙

research

∙ 06/25/2021

Multimodal Few-Shot Learning with Frozen Language Models

When trained at sufficient scale, auto-regressive language models exhibi...

0 Maria Tsimpoukelli, et al. ∙

research

∙ 05/28/2021

Towards mental time travel: a hierarchical memory for reinforcement learning agents

Reinforcement learning agents often forget details of the past, especial...

0 Andrew Kyle Lampinen, et al. ∙

research

∙ 12/15/2020

Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures

Neural networks have achieved success in a wide array of perceptual task...

0 David Ding, et al. ∙

research

∙ 12/10/2020

Imitating Interactive Intelligence

A common vision from science fiction is that robots will one day inhabit...

0 Josh Abramson, et al. ∙

research

∙ 09/03/2020

Grounded Language Learning Fast and Slow

Recent work has shown that large text-based neural language models, trai...

7 Felix Hill, et al. ∙

research

∙ 06/01/2020

Probing Emergent Semantics in Predictive Agents via Question Answering

Recent work has shown how predictive modeling can endow agents with rich...

18 Abhishek Das, et al. ∙

research

∙ 05/19/2020

Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text

Recent work has described neural-network-based agents that are trained w...

0 Felix Hill, et al. ∙

research

∙ 12/12/2019

Extending Machine Language Models toward Human-Level Language Understanding

Language is central to human intelligence. We review recent breakthrough...

34 James L. McClelland, et al. ∙

research

∙ 10/01/2019

Emergent Systematic Generalization in a Situated Agent

The question of whether deep neural networks are good at generalising be...

17 Felix Hill, et al. ∙

research

∙ 09/01/2019

Higher-order Comparisons of Sentence Encoder Representations

Representational Similarity Analysis (RSA) is a technique developed by n...

0 Mostafa Abdou, et al. ∙

research

∙ 05/02/2019

SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

In the last year, new models and methods for pretraining and transfer le...

4 Alex Wang, et al. ∙

research

∙ 04/18/2019

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

Brette contends that the neural coding metaphor is an invalid basis for ...

0 Adam Santoro, et al. ∙

research

∙ 04/02/2019

Analysing Mathematical Reasoning Abilities of Neural Models

Mathematical reasoning---a core ability within human intelligence---pres...

14 David Saxton, et al. ∙

research

∙ 01/31/2019

Learning to Make Analogies by Contrasting Abstract Relational Structure

Analogical reasoning has been a principal focus of various waves of AI r...

0 Felix Hill, et al. ∙

research

∙ 12/03/2018

Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning

Advances in Deep Reinforcement Learning have led to agents that perform ...

0 Aishwarya Agrawal, et al. ∙

research

∙ 08/01/2018

Neural Arithmetic Logic Units

Neural networks can learn to represent and manipulate numerical informat...

6 Andrew Trask, et al. ∙

research

∙ 07/11/2018

Measuring abstract reasoning in neural networks

Whether neural networks can learn abstract reasoning or whether they mer...

0 David G. T. Barrett, et al. ∙

research

∙ 06/05/2018

Learning to Follow Language Instructions with Adversarial Reward Induction

Recent work has shown that deep reinforcement-learning agents can learn ...

14 Dzmitry Bahdanau, et al. ∙

research

∙ 04/20/2018

GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

For natural language understanding (NLU) technology to be maximally usef...

0 Alex Wang, et al. ∙

research

∙ 10/26/2017

Understanding Grounded Language Learning Agents

Neural network-based systems can now learn to locate the referents of wo...

0 Felix Hill, et al. ∙

research

∙ 06/20/2017

Grounded Language Learning in a Simulated 3D World

We are increasingly surrounded by artificially intelligent technology th...

0 Karl Moritz Hermann, et al. ∙

research

∙ 08/06/2016

HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment

We introduce HyperLex - a dataset and evaluation resource that quantifie...

0 Ivan Vulić, et al. ∙

research

∙ 08/02/2016

SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity

Verbs play a critical role in the meaning of sentences, but these ubiqui...

0 Daniela Gerz, et al. ∙

research

∙ 02/10/2016

Learning Distributed Representations of Sentences from Unlabelled Data

Unsupervised methods for learning distributed representations of words a...

0 Felix Hill, et al. ∙

research

∙ 11/07/2015

The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations

We introduce a new test of how well language models capture meaning in c...

0 Felix Hill, et al. ∙

research

∙ 04/02/2015

Learning to Understand Phrases by Embedding the Dictionary

Distributional models that learn rich semantic word representations are ...

0 Felix Hill, et al. ∙

research

∙ 12/19/2014

Embedding Word Similarity with Neural Machine Translation

Neural language models learn word representations, or embeddings, that c...

0 Felix Hill, et al. ∙

research

∙ 10/02/2014

Not All Neural Embeddings are Born Equal

Neural language models learn word representations that capture rich ling...

0 Felix Hill, et al. ∙

Felix Hill

Featured Co-authors