cs.LGMay 21, 2026

World Machine: Towards Generative World Modeling for Time-Series

Authors: Elton Cardoso do NascimentoAlexandre da Silva SimõesEsther Luna ColombiniRicardo Ribeiro GudwinPaula Dornhofer Paro Costa

Organizations: Universidade Estadual de Campinas (UNICAMP), {FEEC, IC} · Universidade Estadual Paulista (UNESP), Instituto de Ciˆencia e Tecnologia, Sorocaba

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.

Explore similar work

CardsList
  1. Looped World Models

    Jun 16, 2026Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang +28World ModelsNeural Architectures