arXiv AI August 26, 2026 By Juntao Fang, Shifeng Xie, Ruichu Cai, Shengji Zheng, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Zhifeng Hao

ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Learning

Read the original on arXiv AI →

ChorusTIC is a training‑free foundation model for multivariate time‑series classification that works across heterogeneous channel configurations without updating task‑specific parameters. It uses Random Subchannel Slot Concatenation and a shared dual‑axis encoder to capture temporal and cross‑channel interactions, mapping variable channel counts into a fixed‑width representation. The model is pretrained on synthetic episodes and achieves strong performance on the UEA‑30 and UCR‑128 archives, handling both full‑context and low‑label scenarios without fitting a target‑specific classifier.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

llms

arXiv Machine Learning

Jul 22

In-Context Time Series Classification with Random Convolutional Features

arXiv:2607. 19234v1 Announce Type: new Abstract: Time series classification is central to domains like medical signal analysis, industrial monitoring, and sensor-based activity recognition, where class information manifests as localized shapes, specific frequencies, temporal shifts, or complex cross-channel interactions.

By Joscha C\"uppers, Jilles Vreeken

benchmarks

arXiv Machine Learning

Sep 1

TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification

arXiv:2608.31013v1 Announce Type: new Abstract: Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for p...

By J\'er\'emie Stym-Popper, Cl\'ement Rambour, Federica Granese, Nicolas Thome, Olivier Bernard

llms rag fine-tuning benchmarks

arXiv AI

Jun 10

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.

By Yunhao Zhang, Ruiying Qi, Jiale Zheng, Jianfeng Zhang, Lujia Pan, Junchi Yan

llms nlp efficiency

arXiv AI

Jun 10

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

arXiv:2606. 10466v1 Announce Type: cross Abstract: In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains.

By Du Yin, Hao Xue, Jinliang Deng, Yang Yang, Shuang Ao, Arian Prabowo, Flora Salim

llms benchmarks

arXiv AI

Jul 9

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

arXiv:2607. 07500v1 Announce Type: cross 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.

By Jaris K\"uken, Shi Bin Hoo, Martin Mr\'az, Frank Hutter, Lennart Purucker

llms benchmarks

arXiv AI

Jul 14

Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference

arXiv:2602. 00620v2 Announce Type: replace-cross Abstract: The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier.

By Juntao Fang, Shifeng Xie, Shengbin Nie, Yuhui Ling, Yuming Liu, Zijian Li, Keli Zhang, Lujia Pan, Themis Palpanas, Ruichu Cai

llms safety

One email a morning, machine-written

Related stories

In-Context Time Series Classification with Random Convolutional Features

TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification

Time Series as Language: A Universal Tokenizer for General-Purpose Time Series Foundation Models

UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation

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

Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference