The relational bottleneck as an inductive bias for efficient abstraction
A central challenge for cognitive science is to explain how abstract concepts are acquired
from limited experience. This has often been framed in terms of a dichotomy between …
from limited experience. This has often been framed in terms of a dichotomy between …
Bayesian models of conceptual development: Learning as building models of the world
A Bayesian framework helps address, in computational terms, what knowledge children start
with and how they construct and adapt models of the world during childhood. Within this …
with and how they construct and adapt models of the world during childhood. Within this …
Intuitive physics learning in a deep-learning model inspired by developmental psychology
Abstract 'Intuitive physics' enables our pragmatic engagement with the physical world and
forms a key component of 'common sense'aspects of thought. Current artificial intelligence …
forms a key component of 'common sense'aspects of thought. Current artificial intelligence …
Dynamic visual reasoning by learning differentiable physics models from video and language
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
The child as hacker
The scope of human learning and development poses a radical challenge for cognitive
science. We propose that developmental theories can address this challenge by adopting …
science. We propose that developmental theories can address this challenge by adopting …
From task structures to world models: what do LLMs know?
In what sense does a large language model (LLM) have knowledge? We answer by
granting LLMs 'instrumental knowledge': knowledge gained by using next-word generation …
granting LLMs 'instrumental knowledge': knowledge gained by using next-word generation …
The violation-of-expectation paradigm: A conceptual overview.
For over 35 years, the violation-of-expectation paradigm has been used to study the
development of expectations in the first 3 years of life. A wide range of expectations has …
development of expectations in the first 3 years of life. A wide range of expectations has …
Language models, agent models, and world models: The law for machine reasoning and planning
Despite their tremendous success in many applications, large language models often fall
short of consistent reasoning and planning in various (language, embodied, and social) …
short of consistent reasoning and planning in various (language, embodied, and social) …
Physion: Evaluating physical prediction from vision in humans and machines
While current vision algorithms excel at many challenging tasks, it is unclear how well they
understand the physical dynamics of real-world environments. Here we introduce Physion, a …
understand the physical dynamics of real-world environments. Here we introduce Physion, a …
Commonsense psychology in human infants and machines
Human infants are fascinated by other people. They bring to this fascination a constellation
of rich and flexible expectations about the intentions motivating people's actions. Here we …
of rich and flexible expectations about the intentions motivating people's actions. Here we …