TimEE: End-to-end Time Series Classification via In-Context Learning

• URL: http://arxiv.org/abs/2607.07500v1
• Date: Wed, 08 Jul 2026 14:58:06 GMT
• Title: TimEE: End-to-end Time Series Classification via In-Context Learning
• Abstract summary: Time series classification (TSC) is dominated by a two-stage paradigm.<n>We introduce TimEE, a foundation model for end-to-end TSC via in-context learning.<n>TimEE is the first purely synthetic-pretrained model to reach state-of-the-art performance on the UCR benchmark.
• Score: 42.26457535497941
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top. While effective, this decoupling optimizes representation learning independently of the classification objective, requires per-dataset training, and prevents the model from exploiting label information during inference. We introduce TimEE, a 4.5M-parameter foundation model for end-to-end TSC via in-context learning. Given a labeled support set and a query time series, TimEE directly outputs a predicted class distribution in a single forward pass with no per-dataset training required. Following the prior-data fitted network (PFN) framework, TimEE is meta-trained exclusively on synthetic TSC tasks, where each task contains time series with distinct class identities arising from structured distributional shifts in the generative process. Despite seeing no real time series during pre-training, TimEE ranks first in ROC AUC (and third on accuracy) on the UCR benchmark among all compared methods, which include both foundation models and supervised deep learning baselines. To our knowledge, TimEE is the first purely synthetic-pretrained model to reach state-of-the-art performance on the UCR benchmark. These results establish end-to-end ICL with synthetic priors as a compelling, largely unexplored direction for TSC, with scaling, prior design, and richer generation mechanisms as natural avenues for improvement. Code is publicly available at http://github.com/automl/timee.

Related papers

• ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning [52.72143039958434]
  We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations.<n>ChorusTIC maps variable channel configurations into a fixed-width representation independent of the original channel count.<n>It calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning.
  arXiv  Detail & Related papers  (2026-08-25T03:45:24Z)
• Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models [58.73838451441261]
  We introduce UniTok, a universal tokenizer that transforms continuous time series (TS) into discrete tokens, and UniTok-FM, a foundation model pretrained via NTP on these tokens.<n>UniTok-FM is a general-purpose foundation model that supports zero-shot and prompt-boosted forecasting, as well as few-shot generation and classification via training-free in-context inference.
  arXiv  Detail & Related papers  (2026-05-31T16:04:11Z)
• Prototype-Guided Classification Sub-Task Decoupling Framework: Enhancing Generalization and Interpretability for Multivariate Time Series [17.242128977027246]
  Time Series Classification (TSC) is a long-standing research problem that has gained increasing attention in recent years.<n>We propose PDFTime, a prototype-guided framework that reformulates time series classification as a multi-stage decision process.<n>To our knowledge, PDFTime is the first framework to reformulate time series classification as a decoupled, multi-stage similarity-based reasoning process.
  arXiv  Detail & Related papers  (2026-05-21T06:45:50Z)
• A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks [0.7677431882779153]
  In-context learning (ICL) allows a model to adapt at inference time by conditioning on examples rather than updating parameters.<n>We present a foundation model for instruction-conditioned in-context time-series tasks based on a quantile-regression T5 encoder-decoder.
  arXiv  Detail & Related papers  (2026-03-23T21:24:41Z)
• TiCT: A Synthetically Pre-Trained Foundation Model for Time Series Classification [24.157185193971856]
  We introduce TiCT, a transformer-based model pre-trained exclusively on synthetic data to perform in-context classification.<n> TiCT achieves competitive performance against state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2025-11-24T20:57:55Z)
• Chronos: Learning the Language of Time Series [79.38691251254173]
  Chronos is a framework for pretrained probabilistic time series models. We show that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks.
  arXiv  Detail & Related papers  (2024-03-12T16:53:54Z)
• Structural Self-Supervised Objectives for Transformers [3.018656336329545]
  This thesis focuses on improving the pre-training of natural language models using unsupervised raw data. In the first part, we introduce three alternative pre-training objectives to BERT's Masked Language Modeling (MLM) In the second part, we proposes self-supervised pre-training tasks that align structurally with downstream applications.
  arXiv  Detail & Related papers  (2023-09-15T09:30:45Z)
• Towards Similarity-Aware Time-Series Classification [51.2400839966489]
  We study time-series classification (TSC), a fundamental task of time-series data mining. We propose Similarity-Aware Time-Series Classification (SimTSC), a framework that models similarity information with graph neural networks (GNNs)
  arXiv  Detail & Related papers  (2022-01-05T02:14:57Z)
• Document Ranking with a Pretrained Sequence-to-Sequence Model [56.44269917346376]
  We show how a sequence-to-sequence model can be trained to generate relevance labels as "target words" Our approach significantly outperforms an encoder-only model in a data-poor regime.
  arXiv  Detail & Related papers  (2020-03-14T22:29:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.