CMoS, a linear chunk-wise model with per-channel mixing of shared correlation matrices, achieves competitive long-term forecasting accuracy on seven benchmarks while using up to 100x fewer parameters than DLinear.
Moment: A family of open time-series foundation models
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
-
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial Correlations
CMoS, a linear chunk-wise model with per-channel mixing of shared correlation matrices, achieves competitive long-term forecasting accuracy on seven benchmarks while using up to 100x fewer parameters than DLinear.