Papers › SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq...

SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inference

11 Mar 2024arXiv:2403.07088archive 2025-07-28

Yanming Liu, Xinyue Peng, Shi Bo, Ningjing Sang, Yafeng Yan, Xiaolan Ke, Zhiting Zheng, Shaobo Liu, Songhang Deng, Jiannan Cao, Le Dai, Xingzu Liu, Ruilin Nong, Weihao Liu

Large language models(LLMs) have shown its outperforming ability on various tasks and question answering. However, LLMs require substantial memory storage on low-resource devices. More critically, the computational speed on these devices is also severely limited. In this paper, we propose SPA(Side Plugin Adaption), a lightweight architecture for fast on-devices inference on the constraints of strict on-devices computation and memory constraints. Compared with other on-devices seq2seq generation, SPA could make a fast and stable inference on low-resource constraints, allowing it to obtain cost effiency. Our method establish an interaction between a pretrained LLMs on-cloud and additive parameters on-devices, which could provide the knowledge on both pretrained LLMs and featured personal feature. Further more, SPA provides a framework to keep feature-base parameters on low computational devices while leave the parameters containing general information on the high computational devices.

PaperPDFCode

Code

oceanntwt/spa officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Question AnsweringSingle Particle Analysis

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

LSTMSPEEDSeq2SeqSigmoid ActivationTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections