Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Langer, Patrick, Kaar, Thomas, Rosenblattl, Max, Xu, Maxwell A., Chow, Winnie, Maritsch, Martin, Jakob, Robert, Wang, Ning, Liu, Juncheng, Verma, Aradhana, Han, Brian, Kim, Daniel Seung, Chubb, Henry, Ceresnak, Scott, Zahedivash, Aydin, Sandhu, Alexander Tarlochan Singh, Rodriguez, Fatima, McDuff, Daniel, Fleisch, Elgar, Aalami, Oliver, Barata, Filipe, Schmiedmayer, Paul
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2510.02410
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912905479323648
author Langer, Patrick
Kaar, Thomas
Rosenblattl, Max
Xu, Maxwell A.
Chow, Winnie
Maritsch, Martin
Jakob, Robert
Wang, Ning
Liu, Juncheng
Verma, Aradhana
Han, Brian
Kim, Daniel Seung
Chubb, Henry
Ceresnak, Scott
Zahedivash, Aydin
Sandhu, Alexander Tarlochan Singh
Rodriguez, Fatima
McDuff, Daniel
Fleisch, Elgar
Aalami, Oliver
Barata, Filipe
Schmiedmayer, Paul
author_facet Langer, Patrick
Kaar, Thomas
Rosenblattl, Max
Xu, Maxwell A.
Chow, Winnie
Maritsch, Martin
Jakob, Robert
Wang, Ning
Liu, Juncheng
Verma, Aradhana
Han, Brian
Kim, Daniel Seung
Chubb, Henry
Ceresnak, Scott
Zahedivash, Aydin
Sandhu, Alexander Tarlochan Singh
Rodriguez, Fatima
McDuff, Daniel
Fleisch, Elgar
Aalami, Oliver
Barata, Filipe
Schmiedmayer, Paul
contents LLMs have emerged as powerful tools for interpreting multimodal data. In medicine, they hold particular promise for synthesizing large volumes of clinical information into actionable insights and digital health applications. Yet, a major limitation remains their inability to handle time series. To overcome this gap, we present OpenTSLM, a family of Time Series Language Models (TSLMs) created by integrating time series as a native modality to pretrained LLMs, enabling reasoning over multiple time series of any length. We investigate two architectures for OpenTSLM. The first, OpenTSLM-SoftPrompt, models time series implicitly by concatenating learnable time series tokens with text tokens via soft prompting. Although parameter-efficient, we hypothesize that explicit time series modeling scales better and outperforms implicit approaches. We thus introduce OpenTSLM-Flamingo, which integrates time series with text via cross-attention. We benchmark both variants against baselines that treat time series as text tokens or plots, across a suite of text-time-series Chain-of-Thought (CoT) reasoning tasks. We introduce three datasets: HAR-CoT, Sleep-CoT, and ECG-QA-CoT. Across all, OpenTSLM models outperform baselines, reaching 69.9 F1 in sleep staging and 65.4 in HAR, compared to 9.05 and 52.2 for finetuned text-only models. Notably, even 1B-parameter OpenTSLM models surpass GPT-4o (15.47 and 2.95). OpenTSLM-Flamingo matches OpenTSLM-SoftPrompt in performance and outperforms on longer sequences, while maintaining stable memory requirements. By contrast, SoftPrompt grows exponentially in memory with sequence length, requiring around 110 GB compared to 40 GB VRAM when training on ECG-QA with LLaMA-3B. Expert reviews by clinicians find strong reasoning capabilities exhibited by OpenTSLMs on ECG-QA. To facilitate further research, we provide all code, datasets, and models open-source.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02410
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
Langer, Patrick
Kaar, Thomas
Rosenblattl, Max
Xu, Maxwell A.
Chow, Winnie
Maritsch, Martin
Jakob, Robert
Wang, Ning
Liu, Juncheng
Verma, Aradhana
Han, Brian
Kim, Daniel Seung
Chubb, Henry
Ceresnak, Scott
Zahedivash, Aydin
Sandhu, Alexander Tarlochan Singh
Rodriguez, Fatima
McDuff, Daniel
Fleisch, Elgar
Aalami, Oliver
Barata, Filipe
Schmiedmayer, Paul
Machine Learning
LLMs have emerged as powerful tools for interpreting multimodal data. In medicine, they hold particular promise for synthesizing large volumes of clinical information into actionable insights and digital health applications. Yet, a major limitation remains their inability to handle time series. To overcome this gap, we present OpenTSLM, a family of Time Series Language Models (TSLMs) created by integrating time series as a native modality to pretrained LLMs, enabling reasoning over multiple time series of any length. We investigate two architectures for OpenTSLM. The first, OpenTSLM-SoftPrompt, models time series implicitly by concatenating learnable time series tokens with text tokens via soft prompting. Although parameter-efficient, we hypothesize that explicit time series modeling scales better and outperforms implicit approaches. We thus introduce OpenTSLM-Flamingo, which integrates time series with text via cross-attention. We benchmark both variants against baselines that treat time series as text tokens or plots, across a suite of text-time-series Chain-of-Thought (CoT) reasoning tasks. We introduce three datasets: HAR-CoT, Sleep-CoT, and ECG-QA-CoT. Across all, OpenTSLM models outperform baselines, reaching 69.9 F1 in sleep staging and 65.4 in HAR, compared to 9.05 and 52.2 for finetuned text-only models. Notably, even 1B-parameter OpenTSLM models surpass GPT-4o (15.47 and 2.95). OpenTSLM-Flamingo matches OpenTSLM-SoftPrompt in performance and outperforms on longer sequences, while maintaining stable memory requirements. By contrast, SoftPrompt grows exponentially in memory with sequence length, requiring around 110 GB compared to 40 GB VRAM when training on ECG-QA with LLaMA-3B. Expert reviews by clinicians find strong reasoning capabilities exhibited by OpenTSLMs on ECG-QA. To facilitate further research, we provide all code, datasets, and models open-source.
title OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
topic Machine Learning
url https://arxiv.org/abs/2510.02410