Saved in:
Bibliographic Details
Main Authors: Nascimento, Elton Cardoso do, Simões, Alexandre da Silva, Colombini, Esther Luna, Gudwin, Ricardo Ribeiro, Costa, Paula Dornhofer Paro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.23025
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918517695053824
author Nascimento, Elton Cardoso do
Simões, Alexandre da Silva
Colombini, Esther Luna
Gudwin, Ricardo Ribeiro
Costa, Paula Dornhofer Paro
author_facet Nascimento, Elton Cardoso do
Simões, Alexandre da Silva
Colombini, Esther Luna
Gudwin, Ricardo Ribeiro
Costa, Paula Dornhofer Paro
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_23025
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle World Machine: Towards Generative World Modeling for Time-Series
Nascimento, Elton Cardoso do
Simões, Alexandre da Silva
Colombini, Esther Luna
Gudwin, Ricardo Ribeiro
Costa, Paula Dornhofer Paro
Machine Learning
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.
title World Machine: Towards Generative World Modeling for Time-Series
topic Machine Learning
url https://arxiv.org/abs/2605.23025