PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
Advances in Neural Information Processing Systems , volume=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.LG 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
NPMixer improves multivariate time series forecasting accuracy by combining a data-adaptive wavelet decomposition with hierarchical neighboring patch mixing via MLPs and channel mixing on high-frequency components.
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.
L-Drive adds a latent context with gating and patch-shared relative positional basis functions to improve adaptation to changing segments in multivariate time series forecasting.
citing papers explorer
-
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
PULSE is a physics-informed plug-and-play framework that uses phase-anchored disentanglement, a Phase Router, and statistic-aware mixup to mitigate Phase Amnesia in non-stationary forecasting and achieve strong results with simple backbones.
-
NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting
NPMixer improves multivariate time series forecasting accuracy by combining a data-adaptive wavelet decomposition with hierarchical neighboring patch mixing via MLPs and channel mixing on high-frequency components.
-
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
MS-FLOW uses a capacity-limited sparse routing mechanism to model only critical inter-variable dependencies in time series data, achieving state-of-the-art accuracy on 12 benchmarks with fewer but more reliable connections.
-
Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
A self-supervised method learns a fixed set of disentangled fingerprint tokens from medical time series by combining reconstruction loss with a total coding rate diversity penalty, framed as a disentangled rate-distortion problem.
-
L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
L-Drive adds a latent context with gating and patch-shared relative positional basis functions to improve adaptation to changing segments in multivariate time series forecasting.