English(EN) Compositional Spectral Prompts for LLM-based Online Time Series Forecasting

基于LLM的框架CoSPOT增强在线时间序列预测

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-03 04:00

研究人员开发了一种新的在线时间序列预测框架CoSPOT，该框架利用预训练的大型语言模型（LLM）作为其核心。这种方法解决了现有方法在长期适应和泛化到新模式方面存在的局限性。CoSPOT通过保持LLM冻结并采用基于频域原理的组合谱提示来实现高效的在线适应。这些提示利用输入信号的整体分布来指导模型，显著减少了在线阶段需要更新的参数数量。实验表明，CoSPOT在真实世界数据集上表现优于现有方法，尤其是在存在分布偏移的具有挑战性的在线场景中。 AI

影响增强了LLM在专业预测任务中的能力，有望提高动态环境下的预测准确性。

排序理由该集群包含一篇研究论文，详细介绍了一种使用LLM进行时间序列预测的新颖方法。 [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇研究论文，详细介绍了一种使用LLM进行时间序列预测的新颖方法。 [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Seungyoon Choi, Hyunchul Kim, Jae-Gil Lee, Chanyoung Park · 2026-09-03 04:00

面向基于LLM的在线时间序列预测的组合光谱提示

arXiv:2609.02093v1 Announce Type: new Abstract: To address the sequential and evolving nature of time series, the Online Time Series Forecasting (OTSF) task has been extensively studied in multiple domains. Existing research focuses on adapting to non-stationary environments by e…

本文如何被排名

报道来源 [1]

面向基于LLM的在线时间序列预测的组合光谱提示

相关实体

相关话题