arXiv:2608.05371

Quantum-Structured World Models (QSWMs) for Predictive Latent Dynamics

Hailong Jiang, Md. Emran Hossain, Feng Yu, Jianfeng Zhu, Guilin Zhang, Wulan Guo

Published Aug 5, 2026• 0 citations

Abstract

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

DOI: 10.48550/arxiv.2608.05371

Related papers

Quantum-Inspired Latent Variable Modeling in Multivariate Analysis

Theodoros A. Kyriazos, Mary Poga

Latent variables play a crucial role in psychometric research, yet traditional models often struggle to address context-dependent effects, ambivalent states, and non-commutative measurement processes. This study proposes a quantum-inspired framework for latent variable modeling that employs Hilbert space representations, allowing questionnaire items to be treated as pure or mixed quantum states. By integrating concepts such as superposition, interference, and non-commutative probabilities, the framework captures cognitive and behavioral phenomena that extend beyond the capabilities of classical methods. To illustrate its potential, we introduce quantum-specific metrics—fidelity, overlap, and von Neumann entropy—as complements to correlation-based measures. We also outline a machine-learning pipeline using complex and real-valued neural networks to handle amplitude and phase information. Results highlight the capacity of quantum-inspired models to reveal order effects, ambivalent responses, and multimodal distributions that remain elusive in standard psychometric approaches. This framework broadens the multivariate analysis theoretical and methodological toolkit, offering a dynamic and context-sensitive perspective on latent constructs while inviting further empirical validation in diverse research settings.

StatsFeb 28, 20253 citations

Quantum-Inspired Mathematical Models for Complex Decision Systems

S. Sathiyanbabu, P. Dhanalakshmi, Dr. R. Venugopal +1 more

The increasing complexity of modern decision-making environments has challenged the effectiveness of classical mathematical models. Traditional probabilistic frameworks often struggle to represent uncertainty, ambiguity, contextual dependence, and nonlinear interactions among decision variables. Quantum-inspired mathematical models have emerged as a promising interdisciplinary approach that leverages mathematical principles derived from quantum theory without requiring quantum computing hardware. These models utilize concepts such as superposition, interference, entanglement, and contextuality to represent complex decision processes more accurately. This paper explores the theoretical foundations, mathematical structures, and applications of quantum-inspired decision models in complex systems. The study examines how quantum probability theory provides a more flexible representation of human cognition, organizational decision-making, financial forecasting, and artificial intelligence systems. Furthermore, the paper discusses mathematical formulations, implementation strategies, advantages, challenges, and future research directions. The findings suggest that quantum-inspired models offer significant potential for addressing uncertainty and dynamic interactions in complex decision environments, thereby contributing to the advancement of intelligent decision support systems.

Stanzaleaf International Journal of Multidisciplinary StudiesJun 12, 20260 citations

Decision Control Under Structured Uncertainty Using a Quantum-Inspired Density Matrix Framework

Aman Sharma

Abstract Machine learning systems are increasingly deployed in environments where decision errors carry significant consequences. In such settings, predictive probabilities alone often provide an incomplete basis for decision making, as they do not reveal why uncertainty arises or whether competing hypotheses are present. This limitation can lead to overconfident decisions, particularly when models encounter ambiguous or evolving conditions.This work introduces a quantum-inspired decision framework that represents predictive uncertainty using a density matrix formulation. Without relying on quantum hardware or computational assumptions, the proposed approach models structured interactions among hypotheses through off-diagonal terms in a normalized state representation. An ambiguity-aware adaptive threshold is derived from this structure and applied as a post-hoc decision layer, thereby regulating decisions without modifying or retraining the underlying predictive model.Theoretical analysis clarifies how structured ambiguity differs from scalar uncertainty measures, and controlled synthetic experiments illustrate its impact on decision boundaries and precision–recall behavior. Results show that the proposed method enables selective suppression of decisions in ambiguous regions while maintaining interpretability and controllability. By bridging uncertainty modeling with practical decision regulation, this framework contributes a simple and extensible mechanism for more reliable AI deployment in high-stakes applications.

Feb 9, 20260 citations

Quantum Generative Models for Computational Fluid Dynamics: A First Exploration of Latent Space Learning in Lattice Boltzmann Simulations

Achraf Hsain, F. M. Abbou

This paper presents the first application of quantum generative models to learned latent space representations of computational fluid dynamics (CFD) data. While recent work has explored quantum models for learning statistical properties of fluid systems, the combination of discrete latent space compression with quantum generative sampling for CFD remains unexplored. We develop a GPU-accelerated Lattice Boltzmann Method (LBM) simulator to generate fluid vorticity fields, which are compressed into a discrete 7-dimensional latent space using a Vector Quantized Variational Autoencoder (VQ-VAE). The central contribution is a comparative analysis of quantum and classical generative approaches for modeling this physics-derived latent distribution: we evaluate a Quantum Circuit Born Machine (QCBM) and Quantum Generative Adversarial Network (QGAN) against a classical Long Short-Term Memory (LSTM) baseline. Under our experimental conditions, both quantum models produced samples with lower average minimum distances to the true distribution compared to the LSTM, with the QCBM achieving the most favorable metrics. This work provides: (1)~a complete open-source pipeline bridging CFD simulation and quantum machine learning, (2)~the first empirical study of quantum generative modeling on compressed latent representations of physics simulations, and (3)~a foundation for future rigorous investigation at this intersection.

arXiv:2512.22672Dec 27, 20250 citations

Toward quantum-aware machine learning: Improved prediction of quantum dissipative dynamics via complex valued neural networks

Muhammad Atif, Arif Ullah, Ming Yang

Accurately modeling quantum dissipative dynamics remains challenging due to environmental complexity and non-Markovian memory effects. Although machine learning provides a promising alternative to conventional simulation techniques, most existing models employ real-valued neural networks (RVNNs) that inherently mismatch the complex-valued nature of quantum mechanics. By decoupling the real and imaginary parts of the density matrix, RVNNs can obscure essential amplitude-phase correlations, compromising physical consistency. Here, we introduce complex-valued neural networks (CVNNs) as a physics-consistent framework for learning quantum dissipative dynamics. CVNNs operate directly on complex-valued inputs, preserve the algebraic structure of quantum states, and naturally encode quantum coherences. Through numerical benchmarks on the spin-boson model and few variants of the Fenna-Matthews-Olson complex, we demonstrate that CVNNs outperform RVNNs in convergence speed, training stability, and physical fidelity-including significantly improved trace conservation and Hermiticity. These advantages increase with system size and coherence complexity, establishing CVNNs as a robust, scalable, quantum-aware classical approach for simulating open quantum systems in the pre-fault-tolerant quantum era.

arXiv:2601.03964The Journal of Chemical PhysicsMar 2, 20261 citation

Quantum-Gated Recurrent World Models: Investigating the Effects of Integrating Quantum RNNs into Model-Based Reinforcement Learning

Tobias Frank Hollmann

Model-based reinforcement learning (MBRL) aims to reduce the number of environment interactions by learning an internal model of the environment that supports policy training by providing learned transition dynamics. The fidelity and stability of this model are of crucial importance. While state-of-the-art methods typically employ large, parameter-heavy architectures to capture complex transition dynamics, creating compact yet expressive models remains an open challenge. Recent advances in quantum computing have motivated the exploration of quantum machine learning models as parameter-efficient architectures capable of modeling complex relationships. In this thesis, we investigate the feasibility of employing hybrid quantum-classical architectures to model the recurrent transition dynamics in MBRL. We propose an evaluation framework based on World Models, in which we can seamlessly exchange different variants of recurrent cells in the state-transition model. This allows us to evaluate quantumenhanced recurrent models against a classical baseline with regard to single-step prediction accuracy, multi-step rollout stability, downstream policy performance, and generalization to unseen environment scenarios. All experiments are conducted in a real-world-inspired autonomous driving simulation environment with multimodal sensor input. We use a multi-fold evaluation process and conduct a large-scale hyperparameter optimization. Our results demonstrate that quantum-enhanced recurrent models achieve comparable performance to classical architectures while requiring substantially fewer parameters. Although no clear quantum advantage is observed, our findings demonstrate the feasibility of hybrid quantum architectures for learning latent dynamics and provide a foundation for future research on integrating quantum machine learning into MBRL.

Mar 2, 20260 citations