UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis

Yunhao Zhang, Minghao Liu, Shengyang Zhou, Junchi Yan
2/12/2026

No official code found. Best implementation: Thinklab-SJTU/UP2ME (36 stars, Apache-2.0, last commit 2025-05-12).

Semantic Scholar

Code Implementations(1)

Thinklab-SJTU/UP2MECommunity68%
Apache-2.0

Official implementation of our ICML 2024 paper "UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis"

361Shell, PythonMay 28, 20241 years agoApache-2.0

Similar Papers

Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering

88% match2026

BayesTune: Bayesian Sparse Deep Model Fine-tuning

85% match2026

Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control

83% match2026

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation

83% match1 repo1202026

Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization

83% match1 repo202026

Visual Alignment Pre-training for Sign Language Translation

82% match2026

Cite this paper

@article{zhang2026upme,
  title  = {UP2ME: Univariate Pre-training to Multivariate Fine-tuning as a General-purpose Framework for Multivariate Time Series Analysis},
  author = {Yunhao Zhang and Minghao Liu and Shengyang Zhou and Junchi Yan},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:0cc50b924039e2235e45628c5ab8e5100660d442},
  journal = {ICML 2024 2024}
}

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/0cc50b924039e2235e45628c5ab8e5100660d442.svg)](https://codeofpaper.com/paper/0cc50b924039e2235e45628c5ab8e5100660d442)

Discussion