Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
Zero-shot forecasting of chaotic systems
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Transformers fail to predict catastrophic collapse in unseen parameter regimes of nonlinear dynamical systems, while reservoir computing reliably succeeds.
A single-layer architecture called FlowMixer uses constrained matrix operations and a semi-group property to enable depth-agnostic, interpretable spatiotemporal forecasting with direct eigenmode extraction.
citing papers explorer
-
Is Flow Matching Just Trajectory Replay for Sequential Data?
Flow matching on time series targets a closed-form nonparametric velocity field that is a similarity-weighted mixture of observed transition velocities, making neural models approximations to an ideal memory-augmented dynamical system sampler.
-
Can Transformers predict system collapse in dynamical systems?
Transformers fail to predict catastrophic collapse in unseen parameter regimes of nonlinear dynamical systems, while reservoir computing reliably succeeds.
-
FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting
A single-layer architecture called FlowMixer uses constrained matrix operations and a semi-group property to enable depth-agnostic, interpretable spatiotemporal forecasting with direct eigenmode extraction.