Metraipolis › archive › dc_036ea05f6702
QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities — arXiv:2609.34842
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34842
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:38.201Z
- SHA-256 of the archived text
b38034bddda67495a99772bc06a0b6cae3a3f3f2f672c00941dce9136aa1e60a- Stable URL of this page
https://metraipolis.com/documento/dc_036ea05f6702
How to cite
QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities — arXiv:2609.34842 — arXiv (en), https://arxiv.org/abs/2609.34842 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_036ea05f6702 (Metraipolis archive dc_036ea05f6702, sha256 b38034bddda67495a99772bc06a0b6cae3a3f3f2f672c00941dce9136aa1e60a)
BibTeX
@misc{dc036ea05f6702,
title = {QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities — arXiv:2609.34842},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34842},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_036ea05f6702; sha256 b38034bddda67495a99772bc06a0b6cae3a3f3f2f672c00941dce9136aa1e60a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34842. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing multimodal time series foundation models (TSFMs) typically model heterogeneous modalities through largely shared mechanisms, overlooking the distinct forecasting roles of endogenous and exogenous modalities. In this work, we propose QiYao-M, a role-aware multimodal TSFM that models the two types of modalities separately. For endogenous modalities, to capture how they evolve along with the underlying temporal dynamics, we introduce an Endo-Multimodal Predictor and Endo-Multimodal Supervision to explicitly learn their evolution from history to the future. For exogenous modalities, to generalize across domains and across various modality types and numbers under the scarcity of exo-multimodal pretraining data, we propose an Exo-Multimodal Retrieval Enhancer that enables rapid downstream adaptation without updating the TSFM parameters. We further introduce Endo-Modality Proxy Training to train this retrieval module without exogenous multimodal pretraining data. Extensive experiments across unimodal and multimodal benchmarks demonstrate strong forecasting performance in scenarios both with and without exogenous modalities. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.34842 — 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 2026-10-07T22:14:28.295Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).