SGCMA transfers an HMM state-transition prior learned from text into time series patches, then aligns patch embeddings to language tokens in each state, enabling a frozen GPT-2 to forecast as well as or better than tuned baselines.
Llm4ts: Two-stage fine-tuning for time-series forecasting with pre-trained llms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
contest 1representative citing papers
citing papers explorer
-
Enhancing LLMs for Time Series Forecasting via Structure-Guided Cross-Modal Alignment
SGCMA transfers an HMM state-transition prior learned from text into time series patches, then aligns patch embeddings to language tokens in each state, enabling a frozen GPT-2 to forecast as well as or better than tuned baselines.