Humans are remarkably limited in:(i) how many control-dependent tasks they can execute
simultaneously, and (ii) how intensely they can focus on a single task. These limitations are …

Conceptual abstraction and analogy‐making are key abilities underlying humans' abilities to
learn, reason, and robustly adapt their knowledge to new domains. Despite a long history of …

The recent advent of large language models has reinvigorated debate over whether human
cognitive capacities might emerge in such generic models given sufficient training data. Of …

We study how neural networks trained by gradient descent extrapolate, ie, what they learn
outside the support of the training distribution. Previous works report mixed empirical results …

We tackle the problems of latent variables identification and" out-of-support''image
generation in representation learning. We show that both are possible for a class of …

Human visual reasoning is characterized by an ability to identify abstract patterns from only
a small number of examples, and to systematically generalize those patterns to novel inputs …

The existing methods for evaluating the inference abilities of Large Language Models
(LLMs) have been predominantly results-centric, making it challenging to assess the …

Abstract visual reasoning (AVR) domain encompasses problems solving which requires the
ability to reason about relations among entities present in a given scene. While humans …

We investigate the capabilities of transformer large language models (LLMs) on relational
reasoning tasks involving abstract symbols. Such tasks have long been studied in the …

Abstract Abstract Visual Reasoning (AVR) problems are commonly used to approximate
human intelligence. They test the ability of applying previously gained knowledge …