# Non-equilibrium active noise enhances generative memory in diffusion models

## TL;DR

This paper shows that using active noise in diffusion models improves memory retention and helps generate complex structures more effectively.

## Contribution

Introducing non-equilibrium active noise to enhance generative memory in diffusion models.

## Key findings

- Active noise creates a memory effect by storing semantic information in temporal correlations.
- Active mechanisms slow down information decay compared to passive Brownian motion.
- Non-equilibrium protocols enable earlier and more robust symmetry breaking during generation.

## Abstract

Generative diffusion models have emerged as powerful tools for sampling high-dimensional distributions, yet they typically rely on white gaussian noise and noise schedules to destroy and reconstruct information. Here, we demonstrate that driving the generative process out of equilibrium using active, temporally correlated noise sources fundamentally alters the information thermodynamics of the system. We show that coupling the data to an active non-Markovian bath creates a ‘memory effect’ where high-level semantic information (such as class identity or molecular metastability) is stored in the temporal correlations of auxiliary degrees of freedom. Using Fisher information analysis, we prove that this active mechanism significantly retards the rate of information decay compared to passive Brownian motion. Crucially, this memory effect facilitates an earlier and more robust symmetry breaking (speciation) during the reverse generative process, allowing the system to resolve multi-scale structures, reminiscent of metastable states in molecular configurations that are washed out in the typical noising processes. Our results suggest that non-equilibrium protocols, inspired by active matter physics, offer a thermodynamically distinct and potentially advantageous pathway for recovering high-dimensional energy landscapes using generative diffusion.