Experimental browser for the Atmosphere
New additions 1. Graph neural networks extrapolate out-of-distribution for shortest paths. arxiv.org/abs/2503.19173 2. Round and Round We Go! What makes Rotary Positional Encodings useful?. ICLR 2025. openreview.net/forum?id=Gtv...
Mar 31, 2025, 5:34 PM
{ "uri": "at://did:plc:m4jauf4wb3kt2aveff3ej3jv/app.bsky.feed.post/3llovf4zu5225", "cid": "bafyreic5ig7izwciho7dajj6ry7xtmkfulbshv2r6njcjqtngyxm5bdxaq", "value": { "text": "New additions\n\n1. Graph neural networks extrapolate out-of-distribution for shortest paths. arxiv.org/abs/2503.19173\n\n2. Round and Round We Go! What makes Rotary Positional Encodings useful?. ICLR 2025. openreview.net/forum?id=Gtv...", "$type": "app.bsky.feed.post", "embed": { "$type": "app.bsky.embed.recordWithMedia", "media": { "$type": "app.bsky.embed.external", "external": { "uri": "https://arxiv.org/abs/2503.19173", "thumb": { "$type": "blob", "ref": { "$link": "bafkreieo2hivyhdzmccyiwhlogkzwkdgmcauit643ysuavjamzs5nctvgm" }, "mimeType": "image/jpeg", "size": 182203 }, "title": "Graph neural networks extrapolate out-of-distribution for shortest paths", "description": "Neural networks (NNs), despite their success and wide adoption, still struggle to extrapolate out-of-distribution (OOD), i.e., to inputs that are not well-represented by their training dataset. Addres..." } }, "record": { "$type": "app.bsky.embed.record", "record": { "cid": "bafyreicjcfab4koxlsq7qmxhonobtzmwnjentd56za2qpqo7tchqfjqdzm", "uri": "at://did:plc:m4jauf4wb3kt2aveff3ej3jv/app.bsky.feed.post/3ljxqpoyjt226" } } }, "langs": [ "en" ], "facets": [ { "index": { "byteEnd": 116, "byteStart": 92 }, "features": [ { "uri": "https://arxiv.org/abs/2503.19173", "$type": "app.bsky.richtext.facet#link" } ] }, { "index": { "byteEnd": 233, "byteStart": 203 }, "features": [ { "uri": "https://openreview.net/forum?id=GtvuNrk58a", "$type": "app.bsky.richtext.facet#link" } ] } ], "createdAt": "2025-03-31T17:34:48.060Z" } }