English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Conventional forecasting methods rely on unimodal time series data, limitingtheir ability to exploit rich textual information. Recently, large languagemodels (LLMs) and time series foundation models (TSFMs) have demonstratedpowerful capability in textual reasoning and temporal modeling, respectively.Integrating the strengths of both to construct a multimodal model thatconcurrently leverages both temporal and textual information for futureinference has emerged as a critical research challenge. To address the scarcityof event-series paired data, we propose a decoupled framework: an LLM isemployed to transform textual events into revision instructions, which are thenused to steer the output of TSFM. To implement this framework, we introduceChronoSteer, a multimodal TSFM that can be steered through textual revisioninstructions, effectively bridging LLM and TSFM. Moreover, to mitigate theshortage of cross-modal instruction-series paired data, we devise a two-stagetraining strategy based on synthetic data. In addition, we also construct ahigh-quality multimodal time series forecasting benchmark to address theinformation leakage concerns during evaluation. After integrating with an LLM,ChronoSteer, which is trained exclusively on synthetic data, achieves a 25.7%improvement in prediction accuracy compared to the unimodal backbone and a22.5% gain over the previous state-of-the-art multimodal method.

ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Data