mlsanityData to 14 Oct 2026

MR-ImagenTime: Multi-Resolution Time Series Generation through Dual Image Representations

arXiv 2603.28253 ↗First posted 30 Mar 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Time series forecasting is vital across many domains, yet existing models struggle with fixed-length inputs and inadequate multi-scale modeling. We propose MR-CDM, a framework combining hierarchical multi-resolution trend decomposition, an adaptive embedding mechanism for variable-length inputs, and a multi-scale conditional diffusion process. Evaluations on four real-world datasets demonstrate that MR-CDM significantly outperforms state-of-the-art baselines (e.g., CSDI, Informer), reducing MAE and RMSE by approximately 6-10 to a certain degree.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 22 references that are in the map. First posted on arXiv 30 Mar 2026.

Builds on

10 of 22 references.

References · 10

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  4. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  5. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,013
  6. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  7. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 337
  8. 2022Diffusion-based Time Series Imputation and Forecasting with Structured State Space Modelscited by 198
  9. 2018Trellis Networks for Sequence Modelingcited by 52
  10. 2024Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Seriescited by 43

Built on by

Not cited yet.