Metraipolis › archive › dc_3f71ddadca84
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives — arXiv:2610.11734
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11734
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:00:55.682Z
- SHA-256 of the archived text
ce7ab3d65d0271e1aa5b2556299d4860f5f9faa9789b89858372533ae92562c2- Stable URL of this page
https://metraipolis.com/documento/dc_3f71ddadca84
How to cite
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives — arXiv:2610.11734 — arXiv (en), https://arxiv.org/abs/2610.11734 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f71ddadca84 (Metraipolis archive dc_3f71ddadca84, sha256 ce7ab3d65d0271e1aa5b2556299d4860f5f9faa9789b89858372533ae92562c2)
BibTeX
@misc{dc3f71ddadca84,
title = {Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives — arXiv:2610.11734},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11734},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f71ddadca84; sha256 ce7ab3d65d0271e1aa5b2556299d4860f5f9faa9789b89858372533ae92562c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11734. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts. Despite progress in zero-shot and task-general forecasting, existing foundation models may still struggle to generalize to complex real-world scenarios. To this end, we develop a primitive-based data synthesis and pretraining pipeline. The synthesis pipeline generates series with temporal primitives shared across domains and then assembles real and generated series into multivariate samples using relational primitives. Afterwards, samples are organized into episodes by assigning distinct channel roles as target variates, past-only covariates, and known-future covariates, ensuring that the model is optimized on predictable variates using available exogenous information. Technically, Timer-M1 further adapts gated two-dimensional Transformer blocks that dynamically allocate cross-variate attention across layers. Across three large-scale forecasting benchmarks, Timer-M1 ranks first on both FEV and TIME and second on GIFT-Eval among most recent time series foundation models. These results support effective primitive-based pretraining as a route to robust general forecasting technique across domains and task settings. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.11734 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:47:01.891Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).