Collected sources and patterns will appear here. Add from search or the patterns library.
(Tensor<LatentState>, Tensor<FutureTimestamps>) -> Tensor<ExtrapolatedStates>
Model latent trajectory dynamics continuously over time to project future states at arbitrary timestamps.
Problem it solves
Discrete-step models cannot evaluate state changes or make predictions at arbitrary, non-grid future points.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.