Mixture-of-experts fusing multiple pretrained forecasters achieves strongest performance on influenza time series, with pretraining gains largest at longer horizons when domain-aligned and LLM methods underperforming.
Interpreting county-level covid-19 infections using transformer and deep learning time series models,
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
-
Understanding Key Features of Time Series Foundation Models from Epidemic Forecasting
Mixture-of-experts fusing multiple pretrained forecasters achieves strongest performance on influenza time series, with pretraining gains largest at longer horizons when domain-aligned and LLM methods underperforming.