Align before Fuse: Vision and Language Representation Learning with Momentum Distillation · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2107.07651/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTAlign before Fuse: Vision and Language Representation Learning with Momentum Distillation — mentioned by margorczynskihttps://news.ycombinator.com/item?id=34970745urn:hackerpapers:mention:2107.07651:34970745Tue, 28 Feb 2023 16:00:26 GMT<p>From what I understand the basis for their model are these two described in these papers: https://arxiv.org/abs/2107.07651 https://arxiv.org/abs/2208.13628 Lot of tricks put together for a great final result it seems</p><p><a href="https://hackerpaper.kaipfister.de/p/2107.07651/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV