Pre-Print

We consider concept generalization at a large scale in the diverse and natural visual spectrum. Established computational modes (i.e., …

We study embodied reference understanding, the task of locating referents using embodied gestural signals and language references. …

Despite the tremendous success, existing machine learning models still fall short of human-like systematic generalization – …

Generating dexterous grasping has been a long-standing and challenging robotic task. Despite recent progress, existing methods …

Theoretical ideas and empirical research have shown us a seemingly surprising result: children, even very young toddlers, demonstrate …

Originated as a philosophical quest, personality discerns how individuals differ from each other in terms of thinking, feeling, and …

Understanding what objects could furnish for humans-namely, learning object affordance-is the crux to bridge perception and action. In …

Humans learn compositional and causal abstraction, i.e., knowledge, in response to the structure of naturalistic tasks. When presented …

Inspired by humans’ remarkable ability to master arithmetic and generalize to unseen problems, we present a new dataset, HINT, to …