Semantic Composition in Visually Grounded Language Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2305.16328/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTSemantic Composition in Visually Grounded Language Models — mentioned by KhoomeiKhttps://news.ycombinator.com/item?id=40370089urn:hackerpapers:mention:2305.16328:40370089Wed, 15 May 2024 17:44:13 GMT<p>Cool connection, hadn&#x27;t seen this before but feels intuitively correct! I also formulate similar (but a bit more out-there) philosophical thoughts on word-meaning as being described by the topological structure of its corresponding images in embedding space, in Section 5.3 of my undergrad thesis [1]. [1] https://arxiv.org/abs/2305.16328</p><p><a href="https://hackerpaper.kaipfister.de/p/2305.16328/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL