565 citations · 1.1k across the 47 of their papers we have counts for
18 papers · 1 filter
When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning
Steven Y. Feng, Noah D. Goodman, Michael C. Frank +3
Outcome-based reinforcement learning can produce models with similar task performance but very different ways of communicating about their mistakes. We study failure disclosure: wh…
Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
Jing Huang, Daniel Wurgaft, Rachit Bansal +6
Larger models learn tasks smaller models do not. What drives this phenomenon? We develop a simple phenomenological argument that power-law scaling already suggests that a larger mo…
Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
Andrew Kyle Lampinen, Martin Engelcke, Yuxuan Li +2
When do machine learning systems fail to generalize, and what mechanisms could improve their generalization? Here, we draw inspiration from cognitive science to argue that one weak…
Distinct Computations Emerge From Compositional Curricula in In-Context Learning
Jin Hwa Lee, Andrew K. Lampinen, Aaditya K. Singh +1
In-context learning (ICL) research often considers learning a function in-context through a uniform sample of input-output pairs. Here, we investigate how presenting a compositiona…
The emergence of sparse attention: impact of data distribution and benefits of repetition
Nicolas Zucchet, Francesco d'Angelo, Andrew K. Lampinen +1
Emergence is a fascinating property of large language models and neural networks more broadly: as models scale and train for longer, they sometimes develop new abilities in sudden…
Learned feature representations are biased by complexity, learning order, position, and more
Andrew Kyle Lampinen, Stephanie C. Y. Chan, Katherine Hermann
Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means…
Passive learning of active causal strategies in agents and language models
Andrew Kyle Lampinen, Stephanie C Y Chan, Ishita Dasgupta +2
What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domai…
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…
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…
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…
What shapes feature representations? Exploring datasets, architectures, and training
Katherine L. Hermann, Andrew K. Lampinen
In naturalistic learning problems, a model's input contains a wide range of features, some useful for the task at hand, and others not. Of the useful features, which ones does the…
Transforming task representations to perform novel tasks
Andrew K. Lampinen, James L. McClelland
An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero-shot), based on its relationship to previous tasks. Humans can exhib…
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…
Zero-shot task adaptation by homoiconic meta-mapping
Andrew K. Lampinen, James L. McClelland
How can deep learning systems flexibly reuse their knowledge? Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challeng…