Experimental browser for the Atmosphere
"LMCompress shatters all previous lossless compression records on four media types: text, images, video and audio." www.nature.com/articles/s42...
May 3, 2025, 2:19 PM
{ "uri": "at://did:plc:ficd3wp64dtpwncefyc3pnls/app.bsky.feed.post/3lobjulhlfc27", "cid": "bafyreieouv3vpimjvebzny4tjgxigjcmkys7obatarcqhxwruueioqbjcq", "value": { "text": "\"LMCompress shatters all previous lossless compression records on four media types: text, images, video and audio.\"\n\nwww.nature.com/articles/s42...", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.external", "external": { "uri": "https://www.nature.com/articles/s42256-025-01033-7", "thumb": { "$type": "blob", "ref": { "$link": "bafkreigklbsa5omw7dnfludgbe33eu4jzvrcdolkunolcvbbwk76b7mrc4" }, "mimeType": "image/jpeg", "size": 39530 }, "title": "Lossless data compression by large models - Nature Machine Intelligence", "description": "Effective lossless compression requires that frequent patterns in the data can be identified. Li et al. explore using deep learning models to more effectively compress text, audio and video data." } }, "langs": [ "en" ], "facets": [ { "index": { "byteEnd": 147, "byteStart": 117 }, "features": [ { "uri": "https://www.nature.com/articles/s42256-025-01033-7", "$type": "app.bsky.richtext.facet#link" } ] } ], "createdAt": "2025-05-03T14:19:39.890Z" } }