Mind games: Game engines as an architecture for intuitive physics

TD Ullman, E Spelke, P Battaglia… - Trends in cognitive …, 2017 - cell.com
We explore the hypothesis that many intuitive physical inferences are based on a mental
physics engine that is analogous in many ways to the machine physics engines used in …

Intuitive physics: Current research and controversies

JR Kubricht, KJ Holyoak, H Lu - Trends in cognitive sciences, 2017 - cell.com
Early research in the field of intuitive physics provided extensive evidence that humans
succumb to common misconceptions and biases when predicting, judging, and explaining …

[图书][B] What babies know: Core Knowledge and Composition volume 1

E Spelke - 2022 - books.google.com
What do infants know? How does the knowledge that they begin with prepare them for
learning about the particular physical, cultural, and social world in which they live? Answers …

Simulation intelligence: Towards a new generation of scientific methods

A Lavin, D Krakauer, H Zenil, J Gottschlich… - arXiv preprint arXiv …, 2021 - arxiv.org
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Visual interaction networks: Learning a physics simulator from video

N Watters, D Zoran, T Weber… - Advances in neural …, 2017 - proceedings.neurips.cc
From just a glance, humans can make rich predictions about the future of a wide range of
physical systems. On the other hand, modern approaches from engineering, robotics, and …

Bayesian models of conceptual development: Learning as building models of the world

TD Ullman, JB Tenenbaum - Annual Review of Developmental …, 2020 - annualreviews.org
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 …

Relational inductive bias for physical construction in humans and machines

JB Hamrick, KR Allen, V Bapst, T Zhu… - arXiv preprint arXiv …, 2018 - arxiv.org
While current deep learning systems excel at tasks such as object classification, language
processing, and gameplay, few can construct or modify a complex system such as a tower of …

A counterfactual simulation model of causal judgments for physical events.

T Gerstenberg, ND Goodman, DA Lagnado… - Psychological …, 2021 - psycnet.apa.org
How do people make causal judgments about physical events? We introduce the
counterfactual simulation model (CSM) which predicts causal judgments in physical settings …

Modeling expectation violation in intuitive physics with coarse probabilistic object representations

K Smith, L Mei, S Yao, J Wu, E Spelke… - Advances in neural …, 2019 - proceedings.neurips.cc
From infancy, humans have expectations about how objects will move and interact. Even
young children expect objects not to move through one another, teleport, or disappear. They …

Comphy: Compositional physical reasoning of objects and events from videos

Z Chen, K Yi, Y Li, M Ding, A Torralba… - arXiv preprint arXiv …, 2022 - arxiv.org
Objects' motions in nature are governed by complex interactions and their properties. While
some properties, such as shape and material, can be identified via the object's visual …