Royi Rassinさんのイラストまとめ

(3) A noun is interpreted simultaneously as an entity and as a modifier of a different entity. For “a seal is opening a letter”, DALL-E 2 tends to attribute the “sealed” property to the letter

(1) A noun with multiple senses in an ambiguous prompt may cause DALL-E 2 to generate the same noun twice, but with different senses. In “a bat is flying over a baseball stadium”, “bat” is visualized as both: a flying mammal and a wooden stick.

New work! :D

We show evidence that DALL-E 2, in stark contrast to humans, does not respect the constraint that each word has a single role in its visual interpretation.

Work with @ravfogel and @Yoav.
BlackboxNLP @ #emnlp2022

Below, "a person is hearing a bat"