Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to
model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …

In this paper, we discuss the development of artificial theory of mind as foundational to an
agent's ability to collaborate with human team members. Agents imbued with artificial social …

Language Models (LMs) can perform new tasks by adapting to a few in-context examples.
For humans, explanations that connect examples to task principles can improve learning …

A hallmark of abstract reasoning is the ability to systematically perform algebraic operations
over variables that can be bound to any entity (Newell, 1980; Fodor and Pylyshyn, 1988): the …

We present symbol tuning-finetuning language models on in-context input-label pairs where
natural language labels (eg," positive/negative sentiment") are replaced with arbitrary …

The widespread success of large language models (LLMs) has been met with skepticism
that they possess anything like human concepts or meanings. Contrary to claims that LLMs …

The Internet of Intelligence is conceived as an emerging networking paradigm, which will
make intelligence as easy to obtain as information. This paper provides an overview of the …

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 …

Summary The Computational Theory of Mind says that the mind is a computing system. It
has a long history going back to the idea that thought is a kind of computation. Its modern …

Building autonomous agents able to grow open-ended repertoires of skills across their lives
is a fundamental goal of artificial intelligence (AI). A promising developmental approach …