{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreied5pzt7aw7arpfqcu6fthr2ej76gfejkvzcmzafazclnr5p6cbhu",
"uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mm5zydppk7p2"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreic2uswpzbrha6kca7jp355icn3wni5k7aomyjo3aaop6eiojetctm"
},
"mimeType": "image/jpeg",
"size": 721506
},
"path": "/news/2026-05-memory-wall-large-scale-ai.html",
"publishedAt": "2026-05-18T17:40:05.000Z",
"site": "https://techxplore.com",
"tags": [
"Computer Sciences"
],
"textContent": "South Korean researchers have successfully developed a core technology that can fundamentally resolve \"memory shortages,\" a chronic bottleneck in large-scale artificial intelligence (AI) training. This technology is a next-generation memory expansion technology based on Ethernet, which is expected to drive infrastructural innovation across the entire AI and big data industries in the future.",
"title": "Researchers break the 'memory wall' in large-scale AI training"
}