arXiv cs.CL· Max Rosenblattl, Nikhil Krishnaswamy, Leon Nissen, Manuel Milling, Nicolas Zumarraga, Ning Wang, Thomas Kaar, Robert Jakob, Bj\"orn W. Schuller, Elgar Fleisch, Patrick Langer, Paul Schmiedmayer·· 2 天前AI 评分29
PocketTSLM：在智能手机上本地部署的软提示时间序列语言模型
PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone Reasoning
AI 导读
PocketTSLM 将 OpenTSLM SoftPrompt 部署到消费级智能手机，通过把编码后的时间序列窗口作为嵌入向量注入而非文本 token 化，实现完全端侧推理，推理过程中不传输任何健康数据。
正文 · 原文
Authors:Max Rosenblattl, Nikhil Krishnaswamy, Leon Nissen, Manuel Milling, Nicolas Zumarraga, Ning Wang, Thomas Kaar, Robert Jakob, Björn W. Schuller, Elgar Fleisch, Patrick Langer, Paul Schmiedmayer
Abstract:Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text rather than as temporal evidence. This representation is poorly matched to personal health systems that need to retrieve, route, or summarize sensor evidence while preserving temporal structure. Cloud-hosted time-series language models avoid smartphone limits, but they repeatedly move sensitive physiology off the device and add latency and per-query compute cost. Mobile model alternatives that aggregate time-series data into statistical features or serialize raw samples as text either compress temporal structure or exhaust the context and memory budgets of small on-device models. We present PocketTSLM, a mobile-native deployment of OpenTSLM SoftPrompt, the soft-prompt variant of the OpenTSLM time-series language model. PocketTSLM runs fully on a consumer smartphone by injecting encoded time-series windows as embeddings instead of tokenizing time series as text. A numerical parity protocol verifies identical greedy-decoded token sequences between the Swift port and a Python reference using Apple's MLX machine-learning framework. Answers also match the PyTorch reference, although rationale wording can differ. An on-device context-economics benchmark compares the soft-prompt path with a text-serialized baseline on the same backbone. In our benchmark format, soft-prompting uses approximately 12 times fewer time-series tokens and reduces prompt-prefill cost. PocketTSLM processes 30-second Sleep-EDF electroencephalography clips for sleep staging and a 1,000-sample (10 s) 12-lead electrocardiogram clip from ECG-QA. In comparison, text-serialized baselines exceed the phone's context or memory budget at longer time-series windows. All inference runs entirely on the device, with no health data transmitted during inference.
| Comments: | 15 pages, 3 figures. A version of this paper was accepted at the Workshop on Deploying AI in Healthcare (DAIH) at COLM 2026. Code: this https URL |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21308 [cs.LG] |
| (or arXiv:2610.21308v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21308 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Paul Schmiedmayer [view email]
[v1]
Thu, 15 Oct 2026 05:56:53 UTC (2,861 KB)
来源：arXiv cs.CL · arxiv.org