SOURCE-LINKED INTELLIGENCE

Memory-Conditioned Diffusion Model for Generalized Langevin Dynamics

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Generalized Langevin equations describe non-Markovian dynamics in which the evolution of resolved variables depends on their past. We propose a memory-conditioned diffusion method for learning stochastic flow maps of these dynamics from observed trajectories, without identifying a memory kernel or reconstructing unresolved variables. A compact, recursively updated bank of exponential filters enables the flow map to retain predictive history over multiple time scales without conditioning on long observation windows. The next-step distribution is conditioned on the current observation and this m

Read original source ↗ Open in workspace

recordType

paper

region

Global