跳到正文
arXiv cs.AI· Sicong Liu, Fengmin Wu, Yuan Gao, Bin Guo, Zimu Zhou, Hongkai Wen, Zhiwen Yu·· 4 小时前AI 评分29

AdaFlowLite:面向异步移动数据的可扩展非阻塞推理

AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data

AI 导读

AdaFlowLite 提出面向异步分布式多模态数据的“机会式”推理,部分数据到达即开始推理,无需等待全部模态。该方法采用多模态轻量 Swin Transformer(MMLST)实现实时灵活的数据补全,无需重训练即可适配不同模态与下游任务。实验显示推理延迟最多降低 80.4%、准确率最多提升 62.1%,能耗降低近 50%,还可用于预处理异步数据以增强 LLM 表现。

正文 · 原文

View PDF HTML (experimental)

Abstract:The rise of mobile devices equipped with numerous sensors, such as LiDAR and cameras, has driven the adoption of multi-modal deep intelligence for distributed sensing tasks, such as smart cabins and driving assistance. However, the arrival time of mobile sensory data vary due to modality size and network dynamics, which can lead to delays (if waiting for slow data) or accuracy decline (if inference proceeds without waiting). Moreover, the diversity and dynamic nature of mobile systems exacerbate this challenge. In response, we present a shift to \textit{opportunistic} inference for asynchronous distributed multi-modal data, enabling inference as soon as partial data arrives. While existing methods focus on optimizing modality consistency and complementarity, known as modal affinity, they lack a \textit{computational} approach to control this affinity in open-world mobile environments. % \sysname pioneers the formulation of structured cross-modality affinity in mobile contexts using a hierarchical analysis-based normalized matrix. This approach accommodates the diversity and dynamics of modalities, generalizing across different types and numbers of inputs. Employing an multi-modal lightweight Swin Transformer (MMLST), \sysname facilitates real-time and flexible data imputation, adapting to various modalities and downstream tasks without retraining. Experiments show that \sysname significantly reduces inference latency by up to 80.4\% and enhances accuracy by up to 62.1\%, while achieving nearly a 50\% reduction in energy consumption, outperforming status quo approaches. Also, this method can enhance LLM performance to preprocess asynchronous data.
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.21691 [cs.LG]
  (or arXiv:2611.21691v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.21691

arXiv-issued DOI via DataCite (pending registration)

Related DOI: https://doi.org/10.1109/TMC.2025.3582060

DOI(s) linking to related resources

Submission history

From: Fengmin Wu [view email]
[v1] Mon, 16 Nov 2026 07:55:57 UTC (7,647 KB)

来源:arXiv cs.AI · arxiv.org