FM-LLM uses Fourier token embeddings and a mixture-of-experts decoder to adapt frozen LLMs to time series forecasting, reporting gains over AutoTimes across many benchmarks.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
FM-LLM: A frequency-enhanced mixture-of-experts framework for adapting LLMs to time series forecasting
FM-LLM uses Fourier token embeddings and a mixture-of-experts decoder to adapt frozen LLMs to time series forecasting, reporting gains over AutoTimes across many benchmarks.