Semantic Composition in Visually Grounded Language Models

TL;DR — A Carnegie Mellon honours undergraduate thesis on whether vision-language models compose meaning the way humans do.

How much weight it carries: An undergraduate thesis. Careful work, but a thesis, not a peer-reviewed result.

Where this came from

• Will Manidis’s “most underrated PDF” thread, July 2023 — routing record: The Most Underrated PDF on the Internet (July 2023)

50 pages. A copy is archived locally against link rot; the header links the original source.