Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our
ability to record large neural and behavioural data increases, there is growing interest in …

Creating noise from data is easy; creating data from noise is generative modeling. We
present a stochastic differential equation (SDE) that smoothly transforms a complex data …

Self-supervised representation learning has shown remarkable success in a number of
domains. A common practice is to perform data augmentation via hand-crafted …

Contrastive learning has recently seen tremendous success in self-supervised learning. So
far, however, it is largely unclear why the learned representations generalize so effectively to …

In this work, we investigate an intriguing and prevalent phenomenon of diffusion models
which we term as" consistent model reproducibility'': given the same starting noise input and …

We study causal representation learning, the task of inferring latent causal variables and
their causal relations from high-dimensional functions (“mixtures”) of the variables. Prior …

We study the problem of learning causal representations from unknown, latent interventions
in a general setting, where the latent distribution is Gaussian but the mixing function is …

This work introduces a novel principle we call disentanglement via mechanism sparsity
regularization, which can be applied when the latent factors of interest depend sparsely on …

Understanding the operation of biological and artificial networks remains a difficult and
important challenge. To identify general principles, researchers are increasingly interested …

Humans are able to rapidly understand scenes by utilizing concepts extracted from prior
experience. Such concepts are diverse, and include global scene descriptors, such as the …