Implicitly learning token semantics

HAL 2026 Preprint

View at publisher
Authors: Gary Nan Tie
DOI: 10.13140/rg.2.2.30432.34566
Cited by: 0

Abstract

A fast implicit recurrent deep learning model of semantic attention is proposed for the purposes of large language model next-token and sequence-to-sequence learning.

Fields of Study & Subjects

Topic Modeling Natural Language Processing Techniques Speech Recognition and Synthesis

Publication details

Journal / source
HAL
Publication date
1 January 2026
Language
EN
Document type
Preprint