World models represent a paradigm shift in generative AI, pursuing predictive understanding and controllable simulation of environments in a structured and generalizable way. We present World Machine, a generative world-modeling architecture for time series. It is a transformer-based architecture with latent states that enables adaptation to different amounts of observed data and contexts. This shows an improvement over traditional transformers, which have a computational and memory cost that scales quadratically with the context. Experiments on a proposed synthetic dataset, Toy1D, validate the approach's feasibility, demonstrate capabilities not found in conventional transformers, and highlight the contributions of each component of the training protocol.
@article{arxiv.2605.23025,
title = {World Machine: Towards Generative World Modeling for Time-Series},
author = {Elton Cardoso do Nascimento and Alexandre da Silva Simões and Esther Luna Colombini and Ricardo Ribeiro Gudwin and Paula Dornhofer Paro Costa},
journal= {arXiv preprint arXiv:2605.23025},
year = {2026}
}