NIST · ИТ · 00b46988aab826f6a88b
A generative pre-trained transformer with Kerr-soliton attention
Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement. Attention is a
NIST · ИТОфициальный источник · 2026-05-22
{
"title_en": "A generative pre-trained transformer with Kerr-soliton attention",
"designation": "",
"series": "",
"status": "",
"date": "2026-05-22",
"date_original": "May 22, 2026",
"url": "https://www.nist.gov/publications/generative-pre-trained-transformer-kerr-soliton-attention",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Lindell Williams , Yan Jin , Scott Papp",
"abstract_excerpt_en": "Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement. Attention is a",
"id": "00b46988aab826f6a88b",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "A generative pre-trained transformer with Kerr-soliton attention",
"designation": "",
"series": "",
"status": "",
"date": "2026-05-22",
"date_original": "May 22, 2026",
"url": "https://www.nist.gov/publications/generative-pre-trained-transformer-kerr-soliton-attention",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Lindell Williams , Yan Jin , Scott Papp",
"abstract_excerpt_en": "Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement. Attention is a"
}
],
"translation_state": "none"
}