Beyond Linearity in Attention Projections: The Case for Nonlinear Queries 文章

ArXiv CS.AI2026-05-27NEWSen作者: Marko Karbevski
大语言模型
查看原文 →
关系图谱

Beyond Linearity in Attention Projections: The Case for Nonlinear Queries · 相关技术

相关技术

ORMTTEODEPLAattentionUCTStraight-Through EstimatorSULRepresentation AnchoringReferring expression comprehension (REC)QueryParts-of-Speech (POS) tagsOWSNLIMLPHISForEvaluation Driven DevelopmentDecodeCamouflaged object detectionARGANNtransformersICEGPT