Visual Transformers: Token-based Image Representation and Processing for Computer Vision · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2006.03677/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTVisual Transformers: Token-based Image Representation and Processing for Computer Vision — mentioned by ben_whttps://news.ycombinator.com/item?id=39915569urn:hackerpapers:mention:2006.03677:39915569Wed, 03 Apr 2024 10:23:49 GMT<p>Tokens don&#x27;t have to be units of language, they can be any arbitrary chunk of an input stream: https://arxiv.org/abs/2006.03677 (I&#x27;d be a bit surprised if our brains are transformers; from what I understand, we&#x27;re much more sample-efficient than most of our AI so far).</p><p><a href="https://hackerpaper.kaipfister.de/p/2006.03677/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV