Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2312.17172/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTUnified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action — HN submissionhttps://news.ycombinator.com/item?id=40353755urn:hackerpapers:submission:2312.17172:40353755Tue, 14 May 2024 10:51:48 GMT<p>Scaling Autoregressive Multimodal Models with Vision, Text, Audio, and Action</p><p></p><p>4 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2312.17172/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVUnified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action — mentioned by alok-ghttps://news.ycombinator.com/item?id=38832343urn:hackerpapers:mention:2312.17172:38832343Mon, 01 Jan 2024 15:19:09 GMT<p>Paper: https://arxiv.org/abs/2312.17172 Github: https://github.com/allenai/unified-io-2 Quick read (third party): https://www.marktechpost.com/2024/01/01/meet-unified-io-2-an...</p><p><a href="https://hackerpaper.kaipfister.de/p/2312.17172/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV