Shepard's universal law of generalization is a remarkable hypothesis abo...
Conducting experiments with diverse participants in their native languag...
Understanding the extent to which the perceptual world can be recovered ...
Learning transferable representations by training a classifier is a
well...
Diffusion models are a class of generative models that learn to synthesi...
Recent advances in multimodal training use textual descriptions to
signi...
Strong inductive biases are a key component of human intelligence, allow...
The ability to acquire abstract knowledge is a hallmark of human intelli...
Similarity judgments provide a well-established method for accessing men...
A core problem in cognitive science and machine learning is to understan...