Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
arXiv preprint arXiv:2208.04360 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
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
-
Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
Zeus proposes a multi-scale Transformer with point-wise tokenization and Multi-Objective Temporal Masking to enable tuning-free performance on forecasting, interpolation, and other time series tasks.
-
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.