Accelerated Sequential Flow Matching: A Bayesian Filtering Perspective
This addresses the need for efficient real-time deployment of flow-based models in stochastic dynamical systems, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackled the problem of high inference latency in real-time streaming environments using diffusion and flow-matching models by introducing Sequential Flow Matching, a framework based on Bayesian filtering that initializes generation from previous posteriors, achieving competitive performance with full-step diffusion while requiring only one or few sampling steps for faster sampling.
Sequential prediction from streaming observations is a fundamental problem in stochastic dynamical systems, where inherent uncertainty often leads to multiple plausible futures. While diffusion and flow-matching models are capable of modeling complex, multi-modal trajectories, their deployment in real-time streaming environments typically relies on repeated sampling from a non-informative initial distribution, incurring substantial inference latency and potential system backlogs. In this work, we introduce Sequential Flow Matching, a principled framework grounded in Bayesian filtering. By treating streaming inference as learning a probability flow that transports the predictive distribution from one time step to the next, our approach naturally aligns with the recursive structure of Bayesian belief updates. We provide theoretical justification that initializing generation from the previous posterior offers a principled warm start that can accelerate sampling compared to naïve re-sampling. Across a wide range of forecasting, decision-making and state estimation tasks, our method achieves performance competitive with full-step diffusion while requiring only one or very few sampling steps, therefore with faster sampling. It suggests that framing sequential inference via Bayesian filtering provides a new and principled perspective towards efficient real-time deployment of flow-based models. Our code is available at https://github.com/Graph-COM/Sequential\_Flow\_Matching.