Using games to understand the mind
Board, card or video games have been played by virtually every individual in the world.
Games are popular because they are intuitive and fun. These distinctive qualities of games …
Games are popular because they are intuitive and fun. These distinctive qualities of games …
Using natural language and program abstractions to instill human inductive biases in machines
Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks.
Although meta-learning is a method to endow neural networks with useful inductive biases …
Although meta-learning is a method to endow neural networks with useful inductive biases …
Abstract visual reasoning with tangram shapes
We introduce KiloGram, a resource for studying abstract visual reasoning in humans and
machines. Drawing on the history of tangram puzzles as stimuli in cognitive science, we …
machines. Drawing on the history of tangram puzzles as stimuli in cognitive science, we …
From partners to populations: A hierarchical Bayesian account of coordination and convention.
Languages are powerful solutions to coordination problems: They provide stable, shared
expectations about how the words we say correspond to the beliefs and intentions in our …
expectations about how the words we say correspond to the beliefs and intentions in our …
Communicating natural programs to humans and machines
Abstract The Abstraction and Reasoning Corpus (ARC) is a set of procedural tasks that tests
an agent's ability to flexibly solve novel problems. While most ARC tasks are easy for …
an agent's ability to flexibly solve novel problems. While most ARC tasks are easy for …
Reconciling truthfulness and relevance as epistemic and decision-theoretic utility.
People use language to influence others' beliefs and actions. Yet models of communication
have diverged along these lines, formalizing the speaker's objective in terms of either the …
have diverged along these lines, formalizing the speaker's objective in terms of either the …
DiffVL: scaling up soft body manipulation using vision-language driven differentiable physics
Combining gradient-based trajectory optimization with differentiable physics simulation is an
efficient technique for solving soft-body manipulation problems. Using a well-crafted …
efficient technique for solving soft-body manipulation problems. Using a well-crafted …
Learning with language-guided state abstractions
We describe a framework for using natural language to design state abstractions for
imitation learning. Generalizable policy learning in high-dimensional observation spaces is …
imitation learning. Generalizable policy learning in high-dimensional observation spaces is …
Identifying concept libraries from language about object structure
Our understanding of the visual world goes beyond naming objects, encompassing our
ability to parse objects into meaningful parts, attributes, and relations. In this work, we …
ability to parse objects into meaningful parts, attributes, and relations. In this work, we …
Disentangling abstraction from statistical pattern matching in human and machine learning
The ability to acquire abstract knowledge is a hallmark of human intelligence and is believed
by many to be one of the core differences between humans and neural network models …
by many to be one of the core differences between humans and neural network models …