Abstract
Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal approaches attempt to incorporate textual signals, but they often treat text as static features or use large language models as forecasting backbones, limiting their ability to capture temporal dynamics and increasing computational cost. To address these challenges, we propose TAC-Time, a unified framework that transforms textual information into additional temporal channels. By modeling text features jointly with numerical sequences in a shared temporal backbone, TAC-Time preserves temporal continuity and periodic structures while remaining efficient and scalable. This formulation also enables systematic interpretability analyses. We show strong cross-modal dependencies through attention and frequency-domain analyses, and identify predictive textual signals whose correlation-aware alignment yields partial forecasting improvements. Extensive experiments on real-world multimodal benchmarks demonstrate that TAC-Time outperforms prior methods.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liang, J., Gu, X., Xie, X., Wu, Y., & Wang, X. (2026). TAC-Time: Texts as Channels For Multimodal Time Series Forecasting. https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting
MLA 9
Liang, Jiayi, et al. "TAC-Time: Texts as Channels For Multimodal Time Series Forecasting." https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting.
Chicago (author–date)
Liang, Jiayi, Xiaotian Gu, Xinyu Xie, Yuanbin Wu, and Xiaoling Wang. 2026. "TAC-Time: Texts as Channels For Multimodal Time Series Forecasting." https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting.
Harvard
Liang, J., Gu, X., Xie, X., Wu, Y. and Wang, X. (2026) 'TAC-Time: Texts as Channels For Multimodal Time Series Forecasting', Available at: https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting.
Vancouver
Liang J, Gu X, Xie X, Wu Y, Wang X. TAC-Time: Texts as Channels For Multimodal Time Series Forecasting. https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting
IEEE
J. Liang, X. Gu, X. Xie, Y. Wu, and X. Wang, "TAC-Time: Texts as Channels For Multimodal Time Series Forecasting," https://omanscience.com/en/articles/tac-time-texts-as-channels-for-multimodal-time-series-forecasting.