984 citations · 3.3k across the 41 of their papers we have counts for
45 papers
Why transformers are obviously good models of language
Felix Hill
Nobody knows how language works, but many theories abound. Transformers are a class of neural networks that process language automatically with more success than alternatives, both…
Vision-Language Models as Success Detectors
Yuqing Du, Ksenia Konyushkova, Misha Denil +5
Detecting successful behaviour is crucial for training intelligent agents. As such, generalisable reward models are a prerequisite for agents that can learn to generalise their beh…
The Edge of Orthogonality: A Simple View of What Makes BYOL Tick
Pierre H. Richemond, Allison Tam, Yunhao Tang +3
Self-predictive unsupervised learning methods such as BYOL or SimSiam have shown impressive results, and counter-intuitively, do not collapse to trivial representations. In this wo…
Collaborating with language models for embodied reasoning
Ishita Dasgupta, Christine Kaeser-Chen, Kenneth Marino +4
Reasoning in a complex and ambiguous environment is a key goal for Reinforcement Learning (RL) agents. While some sophisticated RL agents can successfully solve difficult tasks, th…
SemPPL: Predicting pseudo-labels for better contrastive representations
Matko Bošnjak, Pierre H. Richemond, Nenad Tomasev +7
Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method…
Transformers generalize differently from information stored in context vs in weights
Stephanie C. Y. Chan, Ishita Dasgupta, Junkyung Kim +3
Transformer models can use two fundamentally different kinds of information: information stored in weights during training, and information provided ``in-context'' at inference tim…
Meaning without reference in large language models
Steven T. Piantadosi, Felix Hill
The widespread success of large language models (LLMs) has been met with skepticism that they possess anything like human concepts or meanings. Contrary to claims that LLMs possess…
Language models show human-like content effects on reasoning tasks
Ishita Dasgupta, Andrew K. Lampinen, Stephanie C. Y. Chan +5
Reasoning is a key ability for an intelligent system. Large language models (LMs) achieve above-chance performance on abstract reasoning tasks, but exhibit many imperfections. Howe…
Know your audience: specializing grounded language models with listener subtraction
Aaditya K. Singh, David Ding, Andrew Saxe +2
Effective communication requires adapting to the idiosyncrasies of each communicative context--such as the common ground shared with each partner. Humans demonstrate this ability t…
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…
Semantic Exploration from Language Abstractions and Pretrained Representations
Allison C. Tam, Neil C. Rabinowitz, Andrew K. Lampinen +6
Effective exploration is a challenge in reinforcement learning (RL). Novelty-based exploration methods can suffer in high-dimensional state spaces, such as continuous partially-obs…
Can language models learn from explanations in context?
Andrew K. Lampinen, Ishita Dasgupta, Stephanie C. Y. Chan +6
Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We the…
Zipfian environments for Reinforcement Learning
Stephanie C. Y. Chan, Andrew K. Lampinen, Pierre H. Richemond +1
As humans and animals learn in the natural world, they encounter distributions of entities, situations and events that are far from uniform. Typically, a relatively small set of ex…
Feature-Attending Recurrent Modules for Generalization in Reinforcement Learning
Wilka Carvalho, Andrew Lampinen, Kyriacos Nikiforou +2
Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. P…
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…
Dynamical crossover behavior in the relaxation of quenched quantum many-body systems
Aamir Ahmad Makki, Souvik Bandyopadhyay, Somnath Maity +1
A crossover between different power-law relaxation behaviors of many-body periodically driven integrable systems has come to light in recent years. We demonstrate using integrable…
BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation
Thomas Scialom, Felix Hill
Natural language processing (NLP) systems are increasingly trained to generate open-ended text rather than classifying between responses. This makes research on evaluation metrics…
Multimodal Few-Shot Learning with Frozen Language Models
Maria Tsimpoukelli, Jacob Menick, Serkan Cabi +3
When trained at sufficient scale, auto-regressive language models exhibit the notable ability to learn a new language task after being prompted with just a few examples. Here, we p…
Towards mental time travel: a hierarchical memory for reinforcement learning agents
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Andrea Banino +1
Reinforcement learning agents often forget details of the past, especially after delays or distractor tasks. Agents with common memory architectures struggle to recall and integrat…
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…
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…
Grounded Language Learning Fast and Slow
Felix Hill, Olivier Tieleman, Tamara von Glehn +3
Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot…
Probing Emergent Semantics in Predictive Agents via Question Answering
Abhishek Das, Federico Carnevale, Hamza Merzic +8
Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose questio…
Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
Felix Hill, Sona Mokra, Nathaniel Wong +1
Recent work has described neural-network-based agents that are trained with reinforcement learning (RL) to execute language-like commands in simulated worlds, as a step towards an…