WorldTS: תיאור עולם למודלים תקופתיים למתיחת קווים רב-מודליים

תקציר מקורי באנגליתarXiv:2609.31162v1 Announce Type: new 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