Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

ChengAo Shen; Wenchao Yu; Ziming Zhao; Dongjin Song; Wei Cheng; Haifeng Chen; Jingchao Ni

Publications

Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

ChengAo Shen, Wenchao Yu, Ziming Zhao, Dongjin Song, Wei Cheng, Haifeng Chen, and Jingchao Ni

NeurIPS 2025 NeurIPS 2025

Website PDF arXiv Code BibTeX

Main figure of Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting

Abstract

Time series, typically represented as numerical sequences, can also be transformed into images and texts, offering multi-modal views (MMVs) of the same underlying signal. These MMVs can reveal complementary patterns and enable the use of powerful pre-trained large models, such as large vision models (LVMs), for long-term time series forecasting (LTSF). However, as we identified in this work, applying LVMs to LTSF poses an inductive bias towards “forecasting periods”. To harness this bias, we propose DMMV, a novel decomposition-based multi-modal view framework that leverages trend-seasonal decomposition and a novel backcast residual based adaptive decomposition to integrate MMVs for LTSF. Comparative evaluations against 14 state-of-the-art (SOTA) models across diverse datasets show that DMMV outperforms single-view and existing multi-modal baselines, achieving the best mean squared error (MSE) on 6 out of 8 benchmark datasets.

Cite

@inproceedings{shen2025multimodalviewenhancedlarge,
      title={Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting}, 
      author={ChengAo Shen and Wenchao Yu and Ziming Zhao and Dongjin Song and Wei Cheng and Haifeng Chen and Jingchao Ni},
      booktitle={NeurIPS},
      year={2025},
}