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 …

In the history of the quest for human-level artificial intelligence, a number of rival paradigms
have vied for supremacy. Symbolic artificial intelligence was dominant for much of the 20th …

In this paper, we experimentally evaluate the zero-shot performance of GPT-4 against prior
generations of GPT on the entire uniform bar examination (UBE), including not only the …

Large multimodal models (LMMs) extend large language models (LLMs) with multi-sensory
skills, such as visual understanding, to achieve stronger generic intelligence. In this paper …

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 …

Disentangled Representation Learning (DRL) aims to learn a model capable of identifying
and disentangling the underlying factors hidden in the observable data in representation …

The field of meta-learning, or learning-to-learn, has seen a dramatic rise in interest in recent
years. Contrary to conventional approaches to AI where tasks are solved from scratch using …

Modern machine learning has subverted and bypassed the theoretical framework of
Chomsky's generative approach to linguistics, including its core claims to particular insights …

Deep neural networks can achieve great successes when presented with large data sets
and sufficient computational resources. However, their ability to learn new concepts quickly …

Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …