RAVEN proposes a regime-aware MoE architecture with cumulative importance thresholding and correlation-aware weighting to adaptively select temporal context for non-stationary financial forecasting.
WPMixer: Efficient multi- resolution mixing for long-term time series forecasting.Proceedings of the AAAI Conference on Artificial Intelligence, 39(18):19581–19588, April 2025
3 Pith papers cite this work, alongside 46 external citations. Polarity classification is still indexing.
3
Pith papers citing it
46
external citations · Crossref
years
2026 3representative citing papers
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
PRISM claims SOTA GPU workload forecasting (MSE 0.0753, R² 0.9131) via dictionary primitives plus adaptive spectral refinement on Alibaba production traces.
citing papers explorer
-
RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
RAVEN proposes a regime-aware MoE architecture with cumulative importance thresholding and correlation-aware weighting to adaptively select temporal context for non-stationary financial forecasting.
-
Perceive, Route and Modulate: Dynamic Pattern Recalibration for Time Series Forecasting
Dynamic Pattern Recalibration (DPR) adds a perceive-route-modulate pipeline that generates time-aware modulation vectors to recalibrate hidden states in forecasting models, improving performance across architectures with low overhead.
-
PRISM: Dynamic Primitive-Based Forecasting for Large-Scale GPU Cluster Workloads
PRISM claims SOTA GPU workload forecasting (MSE 0.0753, R² 0.9131) via dictionary primitives plus adaptive spectral refinement on Alibaba production traces.