Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process, "iterated learning,"

Consistency Models (CMs) have made significant progress in accelerating the generation of diffusion models. However, their application to high-resolution, text-conditioned image generation in the latent space remains unsatisfactory.

However, zero-shot learning methods still require human instruction set to solve a new task.

In safety-critical applications, machine learning models should generalize well under worst-case distribution shifts, that is, have a small robust risk.

The following lemma is standard in the literature, see e.g.

Our primary focus is the identification of the latent structure in measurement models without parametric assumptions such as linearity or Gaussianity.

Optimizing complex and high-dimensional black-box functions is ubiquitous in science and engineering fields.