arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.03255cs.LGcs.AI
收藏

SciTS: 基于大语言模型的科学时间序列理解与生成

SciTS: Scientific Time Series Understanding and Generation with LLMs

Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Tsinghua University(清华大学);Harbin Institute of Technology(哈尔滨工业大学);University of Science and Technology of China(中国科学技术大学)

Wen Wu, Ziyang Zhang, Liwei Liu, Xuenan Xu, Jimin Zhuang, Ke Fan, Qitan Lv, Junlin Liu, Chen Zhang, Zheqi Yuan, Siyuan Hou, Tianyi Lin, Kai Chen, Bowen Zhou, Chao Zhang

AI总结:

SciTS提出了一种基于LLM的科学时间序列理解与生成框架,通过基准测试发现通用LLM在泛化能力上优于专门模型,并引入TimeOmni框架提升性能。

摘要:

大语言模型(LLMs)的科学推理能力近期引起了广泛关注。时间序列作为科学数据中的基本模态,呈现出独特的挑战,而当前多模态LLMs往往将数值序列编码为文本或转换为图像,这种做法可能无法全面理解和生成科学时间序列。现有的统一时间序列模型通常专门用于预测或分析,其在非周期性、异质性科学信号上的有效性尚不明确。为解决这些不足,我们引入了SciTS基准,涵盖12个科学领域和43个任务,包含超过50000个实例,涵盖从10^0到10^7长度、高达10MHz频率的单变量和多变量信号。我们评估了17种模型,包括纯文本LLMs、多模态LLMs和统一时间序列模型,发现通用LLMs在泛化能力上优于专门的时间序列模型,而将时间序列表示为文本或图像会因序列过长和数值精度丢失而限制性能。我们随后引入TimeOmni框架,使LLMs能够理解和生成时间序列,同时保持与通用LLM训练的兼容性。本工作填补了专用基准和建模框架在科学时间序列方面的空白,为LLMs理解和生成复杂的时空科学数据铺平了道路。

英文摘要:

The scientific reasoning ability of large language models (LLMs) has recently attracted significant attention. Time series, as a fundamental modality in scientific data, presents unique challenges that are often overlooked in current multimodal LLMs, which either encode numerical sequences as text or convert them into images. Such approaches may be insufficient for comprehensive scientific time series understanding and generation. Existing unified time series models typically specialise in either forecasting or analysis, and their effectiveness on non-periodic, heterogeneous scientific signals remains unclear. To address these gaps, we introduce SciTS, a benchmark spanning 12 scientific domains and 43 tasks, with over 50k+ instances, both univariate and multivariate signals ranging from $10^0$ to $10^7$ in length and up to 10~MHz in frequency. We benchmark 17 models, including text-only LLMs, multimodal LLMs, and unified time series models, and find that general-purpose LLMs exhibit stronger generalisability than specialised time series models, while representing time series as text or images limits their performance due to excessively long sequences and loss of numerical precision, respectively. We then introduce TimeOmni, a framework that equips LLMs with the ability to understand and generate time series while remaining compatible with general-purpose LLM training. This work fills a gap in both dedicated benchmarks and modelling frameworks for scientific time series, paving the way for LLMs to understand and generate complex temporal scientific data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑