Video-LLaVA: Learning United Visual Representation by Alignment Before Projection · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2311.10122/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTVideo-LLaVA: Learning United Visual Representation by Alignment Before Projection — mentioned by btbuildemhttps://news.ycombinator.com/item?id=38368753urn:hackerpapers:mention:2311.10122:38368753Tue, 21 Nov 2023 19:31:47 GMT<p>The related paper is here: https://arxiv.org/pdf/2311.10122.pdf I think the TL;DR is &quot;it can tell what&#x27;s in the video and &#x27;reason&#x27; about it&quot;</p><p><a href="https://hackerpaper.kaipfister.de/p/2311.10122/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV