Language pretraining builds a generalizable manifold that supports cross-modal transfer to time series forecasting through linear probes, retrieval, and low-dimensional finetuning alignment.
Title resolution pending
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
-
LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
Language pretraining builds a generalizable manifold that supports cross-modal transfer to time series forecasting through linear probes, retrieval, and low-dimensional finetuning alignment.