In this work, we investigate whether analogical reasoning can enable in-context composition over composable elements of visual stimuli.

Another difficulty is entanglement of the labels.

The image pairs are mined from existing datasets.

In these games, two agents must agree on a communication protocol in order to solve a cooperative task.

Large language models are few-shot learners that can solve diverse tasks from a handful of demonstrations. This implicit understanding of tasks suggests that the attention mechanisms over word tokens may play a role in analogical reasoning. In this work, we investigate whether analogical reasoning can enable in-context composition over composable elements of visual stimuli. First, we introduce a suite of three benchmarks to test the generalization properties of a visual in-context learner. We formalize the notion of an analogy-based in-context learner and use it to design a meta-learning framework called Im-Promptu.