MulTiCast: A Multimodal Time Series Forecasting System
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41655-41657
DOI: 10.1609/aaai.v40i48.42371 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sehyuk Park und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Time-series forecasting plays an essential role in domains such as finance, healthcare, and energy. Yet most existing systems operate in a unimodal setting, overlooking complementary information available from visual and textual modalities. There are surprisingly few time-series forecasting demos, and multimodal, interpretable demos are rarer still. In practice, it is difficult for users to experiment with foundation models on their own time-series data due to strict input requirements, heavy setup burdens, and limited interpretability support. We present MulTiCast, an interactive Multimodal Time series foreCasting system that enables users to combine numerical signals with visual and textual context to improve predictions. The system builds on pretrained models with lightweight adaptation, but its central contribution lies in the interactive demonstration platform. Through a web interface via Hugging Face Spaces, users can load datasets, toggle modality inclusion, and visualize forecasts together with the attention maps of each modality, providing insights into the reasoning path behind the predictions.
Zitieren
APA
Park, S., Han, C., & Chung, H. (2026). MulTiCast: A Multimodal Time Series Forecasting System. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41655-41657. https://doi.org/10.1609/aaai.v40i48.42371
Vancouver
Park S, Han C, Chung H. MulTiCast: A Multimodal Time Series Forecasting System. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41655-41657. doi:10.1609/aaai.v40i48.42371
BibTeX
@article{Park2026,
author = {Park, Sehyuk and Han, Caren and Chung, Hyunsuk},
title = {MulTiCast: A Multimodal Time Series Forecasting System},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41655--41657},
doi = {10.1609/aaai.v40i48.42371}
}
EUVIMED