The proposed framework decomposes retrieval-augmented representations into invariant and dynamic components to improve robustness in zero-shot time series forecasting under distribution shifts.
Cross-rag: Zero-shot retrieval-augmented time series forecasting via cross-attention.arXiv preprint arXiv:2603.14709,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
The proposed framework decomposes retrieval-augmented representations into invariant and dynamic components to improve robustness in zero-shot time series forecasting under distribution shifts.