Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics
For researchers in world models and representation learning, this paper explores whether quantum-inspired structures offer useful inductive biases, but the gains are preliminary and limited to short-term prediction.
The paper introduces Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling, and evaluates complex-valued and density-matrix variants on elementary cellular automata. Results show promising local predictive potential for complex-valued QSWMs but limitations in long-horizon rollout and density-matrix variants.
World models learn latent states that summarize interaction histories, evolve over time, and support prediction, simulation, or planning. Most existing world models represent these states using classical vectors, probability distributions, recurrent hidden states, or transformer activations. In this paper, we introduce Quantum-Structured World Models (QSWMs), a quantum-inspired framework for predictive world modeling with structured latent states, latent transition operators, and measurement-inspired decoding maps. We study whether mathematical structures inspired by quantum theory, such as complex-valued representations and density-matrix-like latents, provide useful inductive biases for world modeling. We establish three foundational properties: classical inclusion, predictive sufficiency, and structured compactness. We then instantiate complex-valued and density-matrix-like QSWM variants and evaluate them on elementary cellular automata against strong classical baselines. Results show promising local predictive potential for complex-valued QSWMs, while also revealing limitations in long-horizon rollout, density-matrix variants