World Machine: Towards Generative World Modeling for Time-Series

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.

Paper

References (13)

09A Path Towards Autonomous MachineIntelligence Version 0.9.2
10NascimentoWorld Machine. Zenodo
11Machine DockerWorld
12Elton Cardoso do Nascimento and Paula CostaWorld Machine - Toy1D Dataset

Scroll for more · 1 remaining

Similar papers

© 2026 NYSGPT2525 LLC