cs.AI updates on arXiv.org 前天 12:22
EcoTransformer: Attention without Multiplication
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

文章提出一种名为EcoTransformer的新型Transformer架构,通过使用拉普拉斯核和L1距离度量,减少了计算量并降低了能耗,同时在NLP、生物信息学和视觉任务中表现出色。

arXiv:2507.20096v1 Announce Type: cross Abstract: The Transformer, with its scaled dot-product attention mechanism, has become a foundational architecture in modern AI. However, this mechanism is computationally intensive and incurs substantial energy costs. We propose a new Transformer architecture EcoTransformer, in which the output context vector is constructed as the convolution of the values using a Laplacian kernel, where the distances are measured by the L1 metric between the queries and keys. Compared to dot-product based attention, the new attention score calculation is free of matrix multiplication. It performs on par with, or even surpasses, scaled dot-product attention in NLP, bioinformatics, and vision tasks, while consuming significantly less energy.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

Transformer 节能 拉普拉斯核 L1距离度量 生物信息学
相关文章