research
∙
06/07/2023
Improving neural network representations using human similarity judgments
Deep neural networks have reached human-level performance on many comput...
share
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...
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...
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...
research
∙
04/08/2022
Semantic Exploration from Language Abstractions and Pretrained Representations
Continuous first-person 3D environments pose unique exploration challeng...
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...
research
∙
03/15/2022
Zipfian environments for Reinforcement Learning
As humans and animals learn in the natural world, they encounter distrib...
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...
research
∙
06/22/2020
What shapes feature representations? Exploring datasets, architectures, and training
In naturalistic learning problems, a model's input contains a wide range...
research
∙
05/08/2020
Transforming task representations to allow deep learning models to perform novel tasks
An important aspect of intelligence is the ability to adapt to a novel t...
research
∙
09/27/2019
Automated curricula through setter-solver interactions
Reinforcement learning algorithms use correlations between policies and ...
research
∙
05/23/2019
Embedded Meta-Learning: Toward more flexible deep-learning models
How can deep learning systems flexibly reuse their knowledge? Toward thi...
research
∙
09/27/2018
An analytic theory of generalization dynamics and transfer learning in deep linear networks
Much attention has been devoted recently to the generalization puzzle in...
research
∙
10/27/2017