ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis

Donghao Luo, Xue Wang
2/12/2026

No official code found. Best implementation: luodhhh/ModernTCN (439 stars, MIT, last commit 2024-04-02).

Semantic Scholar

Code Implementations(1)

luodhhh/ModernTCNCommunity65%
MIT

This is an official implementation of "ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis" (ICLR 2024 Spotlight), https://openreview.net/forum?id=vpJMJerXHU

43956Shell, PythonMar 9, 20242 years agoMIT

Similar Papers

NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation

100% match1 repo62026

CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection

100% match1 repo402026

NeRMo: Learning Implicit Neural Representations for 3D Human Motion Prediction

100% match2026

SDMG: Smoothing Your Diffusion Models for Powerful Graph Representation Learning

100% match1 repo42026

MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction

100% match2026

Residual TPP: A Unified Lightweight Approach for Event Stream Data Analysis

100% match2026

Cite this paper

@article{luo2026moderntcn,
  title  = {ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis},
  author = {Donghao Luo and Xue Wang},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:4ed9e4401a0388fcc0950a0449dcef00805f5f2c},
  journal = {ICLR 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/4ed9e4401a0388fcc0950a0449dcef00805f5f2c.svg)](https://codeofpaper.com/paper/4ed9e4401a0388fcc0950a0449dcef00805f5f2c)

Discussion