TimeRFT applies reinforcement learning with multi-faceted step-wise rewards and informative sample selection to improve generalization and accuracy in TSFM adaptation beyond supervised fine-tuning.
Zhang, and JUN ZHOU
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DSPR decouples temporal patterns and residual dynamics with physics priors to improve accuracy and plausibility in non-stationary industrial forecasting.
citing papers explorer
-
TimeRFT: Stimulating Generalizable Time Series Forecasting for TSFMs via Reinforcement Finetuning
TimeRFT applies reinforcement learning with multi-faceted step-wise rewards and informative sample selection to improve generalization and accuracy in TSFM adaptation beyond supervised fine-tuning.
-
DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting
DSPR decouples temporal patterns and residual dynamics with physics priors to improve accuracy and plausibility in non-stationary industrial forecasting.