Pith. sign in

REVIEW 7 cited by

Timer-XL: Long-Context Transformers for Unified Time Series Forecasting

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 2410.04803 v4 pith:TT5DPV22 submitted 2024-10-07 cs.LG stat.ML

Yong Liu , Guo Qin , Xiangdong Huang , Jianmin Wang , Mingsheng Long This is my paper · ORCID
classification cs.LGstat.ML
keywords seriestimeforecastingtimer-xlunifiedpredictiontokenachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present Timer-XL, a causal Transformer for unified time series forecasting. To uniformly predict multidimensional time series, we generalize next token prediction, predominantly adopted for 1D token sequences, to multivariate next token prediction. The paradigm formulates various forecasting tasks as a long-context prediction problem. We opt for decoder-only Transformers that capture causal dependencies from varying-length contexts for unified forecasting, making predictions on non-stationary univariate time series, multivariate series with complicated dynamics and correlations, as well as covariate-informed contexts that include exogenous variables. Technically, we propose a universal TimeAttention to capture fine-grained intra- and inter-series dependencies of flattened time series tokens (patches), which is further enhanced by deft position embedding for temporal causality and variable equivalence. Timer-XL achieves state-of-the-art performance across task-specific forecasting benchmarks through a unified approach. Based on large-scale pre-training, Timer-XL achieves state-of-the-art zero-shot performance, making it a promising architecture for pre-trained time series models. Code is available at this repository: https://github.com/thuml/Timer-XL.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A balanced sampling strategy over statistically characterized time series patterns lets universal forecasting models train on 78 billion tokens instead of 419 billion, with equal or better zero-shot accuracy.

  2. Investigating Compositional Reasoning in Time Series Foundation Models

    cs.LG 2025-02 conditional novelty 6.0 of 10

    On a benchmark where models train on Fourier components and test on their sums, patch-based Transformers and residual MLP architectures show the strongest compositional generalization, while most standard transformers...

  3. Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Using Fourier basis expansion to build time-frequency features improves long-term and short-term time series forecasting across linear, MLP, and transformer backbones.

  4. TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion

    cs.LG 2026-07 reject novelty 4.0 of 10

    TFGformer combines STFT-based variable graph learning with covariate fusion and claims small MSE improvements over six baselines on seven time series benchmarks.

  5. Large Causal Models for Temporal Causal Discovery

    cs.LG 2026-02 conditional novelty 4.0 of 10

    A transformer pretrained on a large mixed corpus of synthetic and simulated realistic time series can discover lagged causal graphs zero-shot on datasets up to 12 variables, outperforming several classical baselines.

  6. Diffusion Models for Time Series Forecasting: A Survey

    stat.ML 2025-07 conditional novelty 4.0 of 10

    A survey classifies diffusion-based time series forecasting models into a two-axis taxonomy by conditioning source and integration method.

  7. Scaling Transformers for Time Series Forecasting: Do Pretrained Large Models Outperform Small-Scale Alternatives?

    cs.LG 2025-06 reject novelty 3.0 of 10

    LLM4TS_FS achieves the best MSE on four of seven long-term datasets, but the claimed broad advantage of pre-trained large models over small transformers is not consistent across all benchmarks.

Pith tools