EMNLP paper: How VLMs map novel visual concepts to language vs humans

benno_krojer · x · 2026-08-21

The author shares a new paper accepted at EMNLP (Budapest), led by undergrad researcher Ada Tur, with bennokrojer as last author for the first time.

The study examines how vision-language models adopt new visual concepts (illustrated with a funny dog example) and compares how they map those concepts to language versus human learners — an empirical look at multimodal concept learning mechanisms.

Original post →

More from Research

Research channel →