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

ChengAo Shen, Wenchao Yu, Ziming Zhao, Dongjin Song, Wei Cheng +2 more
5/29/2025
cs.LGcs.AI

Official code: D2I-Group/dmmv (31 stars, MIT, last commit 2026-01-02).

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, the state-of-the-art (SOTA) LVM-based forecaster 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 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. The code for this paper is available at: https://github.com/D2I-Group/dmmv.

View on arXivView PDF

Code Implementations(1)

D2I-Group/dmmvOfficial100%
MIT

This is an official repository for "Multi-Modal View Enhanced Large Vision Models for Long-Term Time Series Forecasting".

318Shell, PythonOct 9, 20259 months agoMIT
multi-modaltimeseries-forecasting

Similar Papers

From Images to Signals: Are Large Vision Models Useful for Time Series Analysis?

86% match2025

VIFO: Visual Feature Empowered Multivariate Time Series Forecasting with Cross-Modal Fusion

85% match2025

OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting

83% match2025

VisionTS++: Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones

83% match1 repo392025

Vision-Enhanced Time Series Forecasting via Latent Diffusion Models

83% match2025

MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis

82% match2025

Cite this paper

@article{shen2025multimodal,
  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},
  year   = {2025},
  eprint = {2505.24003},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2505.24003v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2505.24003.svg)](https://codeofpaper.com/paper/2505.24003)

Discussion