Metraipolis › archive › dc_cc8f2d3f2e04
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting — arXiv:2610.06936
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06936
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:40:38.492Z
- SHA-256 of the archived text
31d774af0a62cc7ed24dec934b86c33094afe12e6dca62b11f537b0dcd80829b- Stable URL of this page
https://metraipolis.com/documento/dc_cc8f2d3f2e04
How to cite
QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting — arXiv:2610.06936 — arXiv (en), https://arxiv.org/abs/2610.06936 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc8f2d3f2e04 (Metraipolis archive dc_cc8f2d3f2e04, sha256 31d774af0a62cc7ed24dec934b86c33094afe12e6dca62b11f537b0dcd80829b)
BibTeX
@misc{dccc8f2d3f2e04,
title = {QiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series Forecasting — arXiv:2610.06936},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06936},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc8f2d3f2e04; sha256 31d774af0a62cc7ed24dec934b86c33094afe12e6dca62b11f537b0dcd80829b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06936. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Irregular multivariate time series forecasting is a challenging yet important problem in real-world applications, where observations are often irregularly sampled and asynchronously recorded across variables. Existing time series foundation models are mostly built on regularly sampled sequences, making them difficult to generalize to irregular time intervals and asynchronous cross-variable dependencies. To address these challenges, we propose QiYao-I, a manifold based foundation model for irregular multivariate time series forecasting. Specifically, we introduce a novel sampling-conditioned temporal manifold attention mechanism that maps real timestamps into a learnable temporal manifold feature space and injects temporal manifold biases into attention layers, enabling the model to capture both irregular time intervals and local sampling structures. Further, we propose a dynamic variable interaction mechanism with frequency awareness. It selectively performs cross-variable message passing under asynchronous observations. Extensive experiments on real-world irregular multivariate forecasting benchmarks demonstrate that QiYao-I achieves superior performance compared with both time series foundation models and end-to-end irregular forecasting models, showing strong generalization ability in zero-shot and few-shot settings. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.06936 — 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 2026-10-07T11:19:24.708Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).