Pith. sign in

REVIEW 11 cited by

UniTS: A Unified Multi-Task Time Series Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.00131 v3 pith:POM7N5XQ submitted 2024-02-29 cs.LG cs.AI

Shanghua Gao , Teddy Koker , Owen Queen , Thomas Hartvigsen , Theodoros Tsiligkaridis , Marinka Zitnik This is my paper · ORCID
classification cs.LGcs.AI
keywords seriestimeunitsmodelstasksdatasetsmodelacross
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Although pre-trained transformers and reprogrammed text-based LLMs have shown strong performance on time series tasks, the best-performing architectures vary widely across tasks, with most models narrowly focused on specific areas, such as time series forecasting. Unifying predictive and generative time series tasks within a single model remains challenging. We introduce UniTS, a unified multi-task time series model that utilizes task tokenization to integrate predictive and generative tasks into a single framework. UniTS employs a modified transformer block to capture universal time series representations, enabling transferability from a heterogeneous, multi-domain pre-training dataset-characterized by diverse dynamic patterns, sampling rates, and temporal scales-to a wide range of downstream datasets with varied task specifications and data domains. Tested on 38 datasets across human activity sensors, healthcare, engineering, and finance, UniTS achieves superior performance compared to 12 forecasting models, 20 classification models, 18 anomaly detection models, and 16 imputation models, including adapted text-based LLMs. UniTS also demonstrates strong few-shot and prompt capabilities when applied to new domains and tasks. In single-task settings, UniTS outperforms competitive task-specialized time series models. Code and datasets are available at https://github.com/mims-harvard/UniTS.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. LightGTS: A Lightweight General Time Series Forecasting Model

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A lightweight time series foundation model using period-aligned patches and parallel decoding reports zero-shot and full-shot accuracy on nine benchmarks comparable to much larger models.

  2. Channel Normalization for Time Series Channel Identification

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Replacing shared layer-normalization parameters with per-channel affine parameters improves channel identifiability and forecasting accuracy across multiple time series backbones.

  3. Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions

    cs.LG 2025-05 reject novelty 6.0 of 10

    CHARM is a 7M-parameter self-supervised embedding model for multivariate time series that uses channel descriptions to beat specialized baselines on forecasting, classification, and anomaly detection.

  4. TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts

    cs.LG 2025-01 conditional novelty 6.0 of 10

    TimeDP conditions a diffusion model on prototype assignments extracted from a few example series, achieving strong in-domain and few-shot unseen-domain time series generation.

  5. Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

    cs.LG 2026-07 conditional novelty 5.0 of 10

    WrapFlow combines continuous-time event/gap tokenization with simulation-free residual flow matching on a Transformer to improve irregular multivariate time-series forecasting.

  6. Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting

    stat.ML 2026-07 reject novelty 5.0 of 10

    A two-stage forecaster (SPA trend extraction + LoRA-fine-tuned residual Transformer) that the paper claims beats prior models by 6.56% MASE, though the claim is not robust to its own extended baseline tables.

  7. Modular Foundation Models for Time-Series Perception in Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A gated bank of frozen self-supervised time-series encoders, aligned and aggregated by a Transformer, supports competitive multi-task perception for digital twins and hydro-generator virtual sensing.

  8. Towards Interpretable Time Series Foundation Models

    cs.CL 2025-07 conditional novelty 5.0 of 10

    After fine-tuning on 180 synthetic mean-reverting series annotated by a large multimodal model, small Qwen models can describe trend direction, noise intensity, and extremum location in natural language.

  9. Enhancing Transformer-Based Foundation Models for Time Series Forecasting via Bagging, Boosting and Statistical Ensembles

    cs.LG 2025-08 conditional novelty 4.0 of 10

    On one Belgian electricity load series, bagging, regression stacking, and residual correction reduce MSE relative to standalone Lag-Llama and AutoGluon forecasts, though the reported numbers are inconsistent and lack ...

  10. Bridging the Gap: A Decade Review of Time-Series Clustering Methods

    cs.LG 2024-12 conditional novelty 4.0 of 10

    A unified taxonomy of time-series clustering methods organizes more than 100 algorithms into four categories spanning classical and deep learning approaches.

  11. CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision

    cs.CL 2024-11 conditional novelty 4.0 of 10

    CLaSP trains separate encoders for signals and text with a contrastive loss so that a natural language query can retrieve matching time-series signals without any predefined synonym dictionary.

Pith tools