MoLA adapts a pre-trained short-horizon forecaster to multiple forecast steps via segment-specific mixtures of shared low-rank adapters, reporting modest mean-squared-error gains over the base models on most of eight benchmarks.
End-to-end data-driven weather prediction.Nature, pages 1–3, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting
MoLA adapts a pre-trained short-horizon forecaster to multiple forecast steps via segment-specific mixtures of shared low-rank adapters, reporting modest mean-squared-error gains over the base models on most of eight benchmarks.