SBI matches MCMC posterior accuracy on a SECIR model but runs 15-120 times faster on GPU for 31-day and 201-day inference windows.
A collaborative multiyear, multimodel assessment of seasonal influenza forecasting in the United States
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
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.
A new collaborative hub for nowcasting SARS-CoV-2 variant frequencies at US state level was built and tested; a simple national pooling baseline performed as well as or better than individual models during October 2024–June 2025.
citing papers explorer
-
Simulation-based inference for rapid Bayesian parameter estimation in epidemiological models: a comparison with MCMC
SBI matches MCMC posterior accuracy on a SECIR model but runs 15-120 times faster on GPU for 31-day and 201-day inference windows.