WorldTS: World Modeling for Multimodal Covariate-aware Time Series Forecasting
cs.LG
Submitted: 2026-09-25
Updated: 2026-09-25
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space.
Terminology
Abstract
Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, sequences of observations generally provide only a partial view of the dynamics of the underlying system, with future observations being shaped by latent dynamics. Recent latent-space forecasting methods thus achieve improved performance by predicting future observations from latent-space representations of historical observations rather than directly forecasting future observations in the observation space. Next, while future observations are also shaped by external factors, how to incorporate external, often multimodal, information into forecasting, so that it can shape latent-state formation and evolution directly, remains underexplored. We propose WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance. Specifically, WorldTS employs a two-stage training strategy. First, it learns forecasting-relevant latent state dynamics conditioned on multimodal covariates, yielding encoded future states. Next, the learned state dynamics are frozen, and an observation decoder is trained to map the predicted future states back to future observations. Extensive experiments on 21 real-world datasets offer insight into WorldTS and its effectiveness.
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
- Mastering Diverse Domains through World Models
- Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained Fusion
- Controllable Video Generation: A Survey
- LiveLight: Real-time Streaming Video Relighting with Interactive Control
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
- WeatherGNN: Exploiting Meteo- and Spatial-Dependencies for Local Numerical Weather Prediction Bias-Correction
- TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation
- From Observations to States: Latent Time Series Forecasting
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks