Separable neural architectures as a primitive for unified predictive and generative intelligence

TL;DR

This paper introduces Separable Neural Architectures (SNAs), a unified framework that factorizes high-dimensional mappings into low-arity components, enabling versatile predictive and generative modeling across diverse domains.

Contribution

The paper formalizes SNAs as a structural inductive bias that unifies various neural models and demonstrates their effectiveness in multiple complex tasks.

Findings

SNAs improve modeling of chaotic physical systems.

SNAs enable efficient reinforcement learning for navigation.

SNAs successfully generate multifunctional microstructures.

Abstract

Intelligent systems across physics, language and perception often exhibit factorisable structure, yet are typically modelled by monolithic neural architectures that do not explicitly exploit this structure. The separable neural architecture (SNA) addresses this by formalising a representational class that unifies additive, quadratic and tensor-decomposed neural models. By constraining interaction order and tensor rank, SNAs impose a structural inductive bias that factorises high-dimensional mappings into low-arity components. Separability need not be a property of the system itself: it often emerges in the coordinates or representations through which the system is expressed. Crucially, this coordinate-aware formulation reveals a structural analogy between chaotic spatiotemporal dynamics and linguistic autoregression. By treating continuous physical states as smooth, separable embeddings, SNAs enable distributional modelling of chaotic systems. This approach mitigates the nonphysical drift characteristics of deterministic operators whilst remaining applicable to discrete sequences. The compositional versatility of this approach is demonstrated across four domains: autonomous waypoint navigation via reinforcement learning, inverse generation of multifunctional microstructures, distributional modelling of turbulent flow and neural language modelling. These results establish the separable neural architecture as a domain-agnostic primitive for predictive and generative intelligence, capable of unifying both deterministic and distributional representations.