World Machine is a latent-state transformer for generative time-series world modeling that claims better adaptation and lower scaling costs than standard transformers, validated on synthetic Toy1D data.
Oasis: A Universe in a Transformer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
World Machine: Towards Generative World Modeling for Time-Series
World Machine is a latent-state transformer for generative time-series world modeling that claims better adaptation and lower scaling costs than standard transformers, validated on synthetic Toy1D data.