Small transformers learn to forecast unseen dynamical systems in-context by using delay embeddings to recover the manifold and forecasting its invariant sets via a transfer-operator strategy.
The mechanistic basis of data depen- dence and abrupt learning in an in-context classification task
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
-
Transformers for dynamical systems learn transfer operators in-context
Small transformers learn to forecast unseen dynamical systems in-context by using delay embeddings to recover the manifold and forecasting its invariant sets via a transfer-operator strategy.