Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Xu Liu, Juncheng Liu, Gerald Woo, Taha İbrahim Aksu, Yuxuan Liang +6 more
2/14/2026

No official code found. Best implementation: Time-MoE/Time-MoE (995 stars, Apache-2.0, last commit 2026-03-21).

Semantic Scholar

Code Implementations(1)

Time-MoE/Time-MoECommunity72%
Apache-2.0

[ICLR 2025 Spotlight] Official implementation of "Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts"

995115PythonSep 22, 20247 months agoApache-2.0
deep-learninglarge-modelmachine-learningtime-seriestime-series-forecasting+1 more

Similar Papers

ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation

98% match2026

Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation

97% match2026

HMoRA: Making LLMs More Effective with Hierarchical Mixture of LoRA Experts

97% match2026

Practical Measurements of Translucent Materials with Inter-Pixel Translucency Prior

96% match2026

Hyper-MD: Mesh Denoising with Customized Parameters Aware of Noise Intensity and Geometric Characteristics

96% match2026

Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families

96% match2026

Cite this paper

@article{liu2026moiraimoe,
  title  = {Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts},
  author = {Xu Liu and Juncheng Liu and Gerald Woo and Taha İbrahim Aksu and Yuxuan Liang and Roger Zimmermann and Chenghao Liu and Junnan Li and Silvio Savarese and Caiming Xiong and Doyen Sahoo},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:3f8f68f87b04306b45e7a56687e0d6361d2fbb65},
  journal = {ICML 2025 2025}
}

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/3f8f68f87b04306b45e7a56687e0d6361d2fbb65.svg)](https://codeofpaper.com/paper/3f8f68f87b04306b45e7a56687e0d6361d2fbb65)

Discussion