Výsledky vyhledávání - "Yin, Congrui"

Report

IAPT: Instruction-Aware Prompt Tuning for Large Language Models

Autor: Zhu, Wei, Tian, Aaron Xuxiang, Yin, Congrui, Ni, Yuan, Wang, Xiaoling, Xie, Guotong

Soft prompt tuning is a widely studied parameter-efficient fine-tuning method. However, it has a clear drawback: many soft tokens must be inserted into the input sequences to guarantee downstream performance. As a result, soft prompt tuning is less c

Externí odkaz: http://arxiv.org/abs/2405.18203

Zobrazit plný text záznamu

Report

F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks

Autor: Gao, Xiangxiang, Zhu, Wei, Gao, Jiasheng, Yin, Congrui

Computational complexity and overthinking problems have become the bottlenecks for pre-training language models (PLMs) with millions or even trillions of parameters. A Flexible-Patience-Based Early Exiting method (F-PABEE) has been proposed to allevi

Externí odkaz: http://arxiv.org/abs/2305.11916

Zobrazit plný text záznamu

Periodical

Multi-scale and multi-task learning for human audio forensics based on convolutional networks

Autor: Batista, Paulo, Bilas Pachori, Ram, Yin, Congrui

Publikováno v: Proceedings of SPIE; June 2023, Vol. 12707 Issue: 1 p127074I-127074I-10, 12580337p

Zobrazit plný text záznamu

Conference

Multi-scale and multi-task learning for human audio forensics based on convolutional networks.

Autor: Yin, Congrui

Publikováno v: Proceedings of SPIE; 3/26/2023, Vol. 12482, p127074I-127074I-10, 1p

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání