WorldTS is a new forecasting framework that models latent dynamics conditioned on multimodal covariates to improve time‑series prediction. It uses a two‑stage training process: first learning latent state dynamics from historical data and covariates, then training a decoder to map predicted latent states back to future observations. Experiments on 21 real‑world datasets demonstrate the effectiveness of this approach.
By Yuhan Zhu, Xiangfei Qiu, Hanyin Cheng, Wangmeng Shen, Chenjuan Guo, Bin Yang, Jilin Hu, Christian S. Jensen
arXiv:2609.15087v1 Announce Type: cross
Abstract: Most time series forecasting benchmarks remain numerical-centric and provide limited support for evaluating contextual information that shapes real-w...
By Peng Chen, Zhihao Zhuang, Hongzhou Chen, Junhao Huang, Aiping Yang, Mengsen Wu, Yiding Liu, Xilin Dai, Zewei Dong
The paper introduces TiMi, a framework that enhances time series transformers with a Multimodal Mixture-of-Experts (MMoE) module to incorporate multimodal data, especially textual information, into forecasting. TiMi leverages large language models to generate future inferences that guide predictions, eliminating the need for explicit representation alignment. Experiments show TiMi achieves state‑of‑the‑art performance on sixteen real‑world multimodal forecasting benchmarks, outperforming advanced baselines while maintaining adaptability and interpretability.
By Jiafeng Lin, Yuxuan Wang, Huakun Luo, Jianmin Wang, Zhongyi Pei
arXiv:2610.17856v2 Announce Type: cross
Abstract: Time-series analysis is increasingly studied in multimodal settings, yet most benchmarks pair temporal signals with text or with visualizations deriv...
By Ziyang Zhang, Shenyi Li, Yilin Wang, Ziyun Cui, Bowen Zhou, Wen Wu, Chao Zhang
The paper introduces ACTS-WM, a self‑supervised framework that models latent actions underlying time‑series transitions. It combines a Joint‑Embedding Predictive Architecture encoder with an action‑conditioned world model to predict future representations conditioned on inferred latent actions and task information. Experiments on 22 datasets across four tasks show that ACTS‑WM improves downstream performance compared to pretrained JEPA‑based encoders.
By Chia-Han Kuo, Chengshuai Zhao, Huan Liu, Lo Pang-Yun Ting
The paper introduces LLM-Integrated Bayesian State Space Models (LBS) for multimodal time-series forecasting, combining a state space model backbone with a pretrained large language model to handle both numerical and textual data. LBS allows flexible lookback and forecast windows, principled uncertainty quantification, and improved temporal generalization. Experiments on the TextTimeCorpus benchmark show a 13.20% performance gain over the previous state‑of‑the‑art while providing human‑readable forecast summaries.
By Sungjun Cho, Changho Shin, Suenggwan Jo, Xinya Yan, Shourjo Aditya Chaudhuri, Frederic Sala
ChronoSteer is a decoupled agentic framework that bridges large language models and time series foundation models by learning cross‑modal alignment from synthetic paired supervision. It converts textual events into revision instructions that steer a frozen time‑series model, discretizes these instructions into a compact codebook to reduce semantic divergence, and then refines the predictions with a two‑stage training strategy. The authors also release a leakage‑controlled multimodal benchmark and report a 25.8% improvement in zero‑shot prediction accuracy over the unimodal backbone.
By Chengsen Wang, Qi Qi, Zhongwen Rao, Lujia Pan, Jingyu Wang
The paper introduces MIDAPN, a unified spatiotemporal forecasting backbone that integrates media-general graph adaptation and automatic temporal learning for both multivariate and multimodal time series. It employs a Multimedia Identity-Aware Graph to capture static, dynamic, and latent relationships across media, and a Spectral Prism Convolution for hierarchical temporal analysis. Extensive experiments on 13 multivariate and 12 multimodal datasets show MIDAPN consistently outperforms 16 state‑of‑the‑art TSF models and is compatible with various foundation models.
By Jierui Lei, Wenjian Zhang, Qingyi Yang, Yuyang Hong, Fangzheng Chen, Zhengbo Zhang, Haina Tang, Shiming Xiang
arXiv:2603. 22372v2 Announce Type: replace-cross Abstract: Recent advances in multimodal learning have motivated the integration of auxiliary modalities such as text or vision into time series (TS) forecasting.
By Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn
The paper introduces a generalized multimodal foundation model that can handle arbitrary combinations of modalities and prediction tasks. It trains on large-scale synthetic multimodal datasets with diverse causal structures to learn transferable multimodal correlations. Experiments on 18 real-world datasets across 12 modalities and 11 tasks show competitive performance compared to specialized models without task-specific adaptation.
By Huizi Cui, Zongbo Han, Chenggong Ding, Naichuan Xiao, Jialong Yang, Jingdong Chen, Guangyu Wang, Qinghua Hu, Changqing Zhang
arXiv:2603. 05997v2 Announce Type: replace-cross Abstract: Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across diverse variables.
By Zhi Lei, Chenxi Liu, Hao Miao, Wanghui Qiu, Bin Yang, Chenjuan Guo
arXiv:2606. 06285v1 Announce Type: new Abstract: Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks.
By Ziwen Kan, Yishuo Chen, Kecheng Li, Andrew Wen, Xiaomeng Wang, Liwei Wang, Jihao Duan, Song Wang, Hongfang Liu, Tianlong Chen