AI Paper Atlas

Research map / Time series / Foundation models for time series

Mantis: Lightweight Foundation Model for Time Series Classification

Vasilii Feofanov, Songkang Wen, Shifeng Xie, Simon Roschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik Tiomoko, Quentin Bouniot, Zeynep Akata, Lujia Pan, Jianfeng Zhang and 1 more

ICML 2026 · Time series › Foundation models for time series · approach: Time series foundation models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
concatenate CLS token with mean of other tokens (intermediate layer) (ablation)Mantis · UCRaccuracy: +0.8%Improved
same token concatenation at the last layer (ablation)Mantis · UCRaccuracyNo clear effect
self-ensembling over multiple interpolation lengths (ablation)Mantis · UCRaccuracy: +0.55%Improved
add first-order difference embeddings to self-ensembling (ablation)SE-Mantis · UCRaccuracy: +0.29%Improved
self-ensembling on the 91-dataset UCR subset (ablation)SE-Mantis · UCR-91accuracyNo clear effect
use intermediate layer (layer 3) instead of final layer (ablation)Mantis · UCR (1M synthetic samples)accuracy: 0.78 -> 0.7994Improved
normalize features (Standard scaler) before logistic regression probe (ablation)Mantis · UCRaccuracy: 0.763 -> 0.837Improved
replace contrastive pre-training with masked autoencoder (ablation)Mantis · UCRaccuracy: 0.788 -> 0.716Hurt
replace InfoNCE with triplet loss (ablation)Mantis · UCRaccuracy: 0.788 -> 0.767Hurt
pre-train on synthetic CauKer data instead of equal-size real data (ablation)Mantis · UCRaccuracy: 0.7829 -> 0.7881Improved
use modern transformer (RoPE, RMSNorm, SwiGLU) instead of classical (ablation)Mantis · UCRaccuracy: 0.7989 -> 0.7994Improved
add first-order difference branch to token generator (ablation)Mantis · UCRaccuracyImproved

Later papers that compared with this method

1 later accepted paper reports Mantis as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy