MMODELYST
Papers/World Machine: Towards Generative World Modeling for Time-Series
PAP

World Machine: Towards Generative World Modeling for Time-Series

May 21, 2026

arXiv
Abstract

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.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Elton Cardoso do Nascimento, Alexandre da Silva Simões, Esther Luna Colombini, Ricardo Ribeiro Gudwin, Paula Dornhofer Paro Costa
Your notes (browser-local)
saved
arXiv:2605.23025