Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2605.13833

QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling

Hoang-Quan Nguyen, S. D. Pandey, Ky Luu

Published May 13, 2026• 0 citations
arXivHTMLPDF

Abstract

Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits scalability to long contexts. State-space models (SSMs) provide an efficient alternative with linear-time computation by evolving a latent state through recurrent updates, but their memory is typically formed via additive or linear transitions, which can limit their ability to capture complex global interactions across tokens. In this work, we introduce one of the first studies to leverage the superposition property of quantum systems to enhance state-based sequence modeling. In particular, we propose Quantum Long-Attention Memory (QLAM), a hybrid quantum-classical memory mechanism that can be viewed as a quantum extension of state-space models. Instead of maintaining a classical latent state updated through additive dynamics, QLAM represents the hidden state as a quantum state whose amplitudes encode a superposition of historical information. The state evolves through parameterized quantum circuits conditioned on the input, enabling a non-classical, globally update mechanism. In this way, QLAM preserves the recurrent and linear-time structure of SSMs while fundamentally enriching the memory representation through quantum superposition. Unlike attention mechanisms that explicitly compute pairwise interactions, QLAM implicitly captures global dependencies through the evolution of the quantum state, and retrieves task-relevant information via query-dependent measurements. We evaluate QLAM on sequential variants of standard image classification benchmarks, including sMNIST, sFashion-MNIST, and sCIFAR-10, where images are flattened into token sequences. Across all tasks, QLAM consistently improves over recurrent baselines and transformer-based models.

DOI
10.48550/arxiv.2605.13833

Related papers

Quantum-Enhanced Attention Mechanism in NLP: A Hybrid Classical-Quantum Approach

S. M. Yousuf Iqbal Tomal, Abdullah Al Shafin, Bhattacharjee, Debojit +2 more

Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.

arXiv:2501.15630•Jan 26, 2025•3 citations

Quantum-Inspired Transformers for Scalable Natural Language Processing Applications in Future AI

Priya Vij, Parmanand Yadav

Quantum-Inspired Transformers are a new class of approaches for natural language processing (NLP) that use principles inspired by physical quantum mechanics to encode and process linguistic information. Paper aims to improve both scalability and efficiency for large-scale NLP tasks in the next generation of artificial intelligence (AI). However, traditional transformers can struggle to encode complex semantic relationships across long sequences and can require high levels of compute resources, hence limiting scalability for large datasets and multilingual tasks. In addition, traditional embeddings do not represent multiple contextual meanings simultaneously, which decreases model expressiveness. To address these challenges and maximize the exploration of potential quantum effects in AI, this paper presents a Quantum State Embedding Attention (QSEA) framework that encodes tokens as quantum inspired states with complex-valued amplitudes. Attention, which is based on entangled states, is meant to efficiently capture long-range dependencies while reducing compute and increasing scalability, all without losing a rich understanding of context. Whereas multilingual translation needs to encode both the source similarity and the target language within a smaller semantic representation space. Our experimentation shows that QSEA consistently provides increased accuracy in decoding, measures attention across long sequences, and yields enduring scalability over large multilingual datasets. The evidence demonstrates the potential for QSEA to be the new layer in the future of AI systems, a layer that is scalable and a highperforming NLP application.

Procedia Computer Science•Jan 1, 2026•1 citation

Hybrid Encoding-based Quantum Self Attention for Financial Time Series Analysis

S Lokes, Suresh Reddy, Samuel Yen Chi Chen

Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.

IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)•Apr 6, 2025•1 citation

Quantum-Optimized Selective State Space Model for Efficient Time Series Prediction

Ștefan-Alexandru Jura, Mihai Udrescu, Alexandru Topîrceanu

Long-range time series forecasting remains challenging, as it requires capturing non-stationary and multi-scale temporal dependencies while maintaining noise robustness, efficiency, and stability. Transformer-based architectures such as Autoformer and Informer improve generalization but suffer from quadratic complexity and degraded performance on very long time horizons. State space models, notably S-Mamba, provide linear-time updates but often face unstable training dynamics, sensitivity to initialization, and limited robustness for multivariate forecasting. To address such challenges, we propose the Quantum-Optimized Selective State Space Model (Q-SSM), a hybrid quantum-optimized approach that integrates state space dynamics with a variational quantum gate. Instead of relying on expensive attention mechanisms, Q-SSM employs a simple parametrized quantum circuit (RY-RX ansatz) whose expectation values regulate memory updates adaptively. This quantum gating mechanism improves convergence stability, enhances the modeling of long-term dependencies, and provides a lightweight alternative to attention. We empirically validate Q-SSM on three widely used benchmarks, i.e., ETT, Traffic, and Exchange Rate. Results show that Q-SSM consistently improves over strong baselines (LSTM, TCN, Reformer), Transformer-based models, and S-Mamba. These findings demonstrate that variational quantum gating can address current limitations in long-range forecasting, leading to accurate and robust multivariate predictions.

arXiv:2509.00259•IEEE International Conference on Big Data (BigData)•Dec 8, 2025•0 citations

Quantum-Enhanced Recurrent Neural Networks via Variational Quantum Gating for Battery State of Health Prediction

Yin Xu, Qinglin Liu, Li Gao +1 more

Accurate state-of-health (SOH) estimation for lithium-ion batteries remains a challenging problem due to complex electrochemical degradation mechanisms and long-range temporal dependencies. In this work, we propose a quantum-enhanced recurrent framework, termed QLSTM, in which variational quantum circuits are directly embedded into the gating mechanisms of long short-term memory networks. By replacing classical affine transformations with parameterized unitary operations, the proposed model introduces structured nonlinear transformations into the recurrent state-transition process. Extensive experiments on multiple benchmark battery datasets demonstrate that QLSTM consistently outperforms classical sequence models in both predictive accuracy and robustness, achieving significant reductions in mean absolute error (MAE), with improvements on the order of 20% compared with classical LSTM baselines. Ablation studies further confirm that these improvements arise primarily from quantum-enhanced gating rather than input-level transformations. Additional analyses on qubit scaling and noise robustness reveal that model performance is governed by a balance between expressive capacity and trainability. These results provide empirical evidence that embedding quantum computational primitives within recurrent architectures offers a structurally grounded approach to improving sequence modeling capability. The proposed framework establishes a new design paradigm for integrating quantum operators into temporal learning models, with potential applications in complex dynamical system prediction tasks.

quant-pharXiv:2604.20438•Apr 23, 2026•0 citations

A Hybrid Transformer Architecture with a Quantized Self-Attention Mechanism Applied to Molecular Generation

Anthony M. Smaldone, Yu Shee, Gregory W. Kyro +4 more

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing the computational overhead. Self-attention integrates learnable query and key matrices to calculate attention scores between all pairs of tokens in a sequence. These scores are then multiplied by a learnable value matrix to obtain the output self-attention matrix, enabling the model to effectively capture long-range dependencies within the input sequence. Here, we propose a hybrid quantum-classical self-attention mechanism as part of a transformer decoder, the architecture underlying large language models (LLMs). To demonstrate its utility in chemistry, we train this model on the QM9 dataset for conditional generation, using SMILES strings as input, each labeled with a set of physicochemical properties that serve as conditions during inference. Our theoretical analysis shows that the time complexity of the query-key dot product is reduced from O ( n 2 d ) in a classical model to O ( n 2 log ⁡ d ) in our quantum model, where n and d represent the sequence length and the embedding dimension, respectively. We perform simulations using NVIDIA’s CUDA-Q platform, which is designed for efficient GPU scalability. This work provides a promising avenue for quantum-enhanced natural language processing (NLP).

arXiv:2502.19214•Journal of Chemical Theory and Computation•May 7, 2025•16 citations
Modeling long-range dependencies in sequential data remains a central challenge in machine learning. Transformers address this challenge through attention mechanisms, but their quadratic complexity with respect to sequence length limits scalability to long contexts. State-space models (SSMs) provide an efficient alternative with linear-time computation by evolving a latent state through recurrent updates, but their memory is typically formed via additive or linear transitions, which can limit their ability to capture complex global interactions across tokens. In this work, we introduce one of the first studies to leverage the superposition property of quantum systems to enhance state-based sequence modeling. In particular, we propose Quantum Long-Attention Memory (QLAM), a hybrid quantum-classical memory mechanism that can be viewed as a quantum extension of state-space models. Instead of maintaining a classical latent state updated through additive dynamics, QLAM represents the hidden state as a quantum state whose amplitudes encode a superposition of historical information. The state evolves through parameterized quantum circuits conditioned on the input, enabling a non-classical, globally update mechanism. In this way, QLAM preserves the recurrent and linear-time structure of SSMs while fundamentally enriching the memory representation through quantum superposition. Unlike attention mechanisms that explicitly compute pairwise interactions, QLAM implicitly captures global dependencies through the evolution of the quantum state, and retrieves task-relevant information via query-dependent measurements. We evaluate QLAM on sequential variants of standard image classification benchmarks, including sMNIST, sFashion-MNIST, and sCIFAR-10, where images are flattened into token sequences. Across all tasks, QLAM consistently improves over recurrent baselines and transformer-based models.
Recent advances in quantum computing have opened new pathways for enhancing deep learning architectures, particularly in domains characterized by high-dimensional and context-rich data such as natural language processing (NLP). In this work, we present a hybrid classical-quantum Transformer model that integrates a quantum-enhanced attention mechanism into the standard classical architecture. By embedding token representations into a quantum Hilbert space via parameterized variational circuits and exploiting entanglement-aware kernel similarities, the model captures complex semantic relationships beyond the reach of conventional dot-product attention. We demonstrate the effectiveness of this approach across diverse NLP benchmarks, showing improvements in both efficiency and representational capacity. The results section reveal that the quantum attention layer yields globally coherent attention maps and more separable latent features, while requiring comparatively fewer parameters than classical counterparts. These findings highlight the potential of quantum-classical hybrid models to serve as a powerful and resource-efficient alternative to existing attention mechanisms in NLP.
Quantum-Inspired Transformers are a new class of approaches for natural language processing (NLP) that use principles inspired by physical quantum mechanics to encode and process linguistic information. Paper aims to improve both scalability and efficiency for large-scale NLP tasks in the next generation of artificial intelligence (AI). However, traditional transformers can struggle to encode complex semantic relationships across long sequences and can require high levels of compute resources, hence limiting scalability for large datasets and multilingual tasks. In addition, traditional embeddings do not represent multiple contextual meanings simultaneously, which decreases model expressiveness. To address these challenges and maximize the exploration of potential quantum effects in AI, this paper presents a Quantum State Embedding Attention (QSEA) framework that encodes tokens as quantum inspired states with complex-valued amplitudes. Attention, which is based on entangled states, is meant to efficiently capture long-range dependencies while reducing compute and increasing scalability, all without losing a rich understanding of context. Whereas multilingual translation needs to encode both the source similarity and the target language within a smaller semantic representation space. Our experimentation shows that QSEA consistently provides increased accuracy in decoding, measures attention across long sequences, and yields enduring scalability over large multilingual datasets. The evidence demonstrates the potential for QSEA to be the new layer in the future of AI systems, a layer that is scalable and a highperforming NLP application.
Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.
Long-range time series forecasting remains challenging, as it requires capturing non-stationary and multi-scale temporal dependencies while maintaining noise robustness, efficiency, and stability. Transformer-based architectures such as Autoformer and Informer improve generalization but suffer from quadratic complexity and degraded performance on very long time horizons. State space models, notably S-Mamba, provide linear-time updates but often face unstable training dynamics, sensitivity to initialization, and limited robustness for multivariate forecasting. To address such challenges, we propose the Quantum-Optimized Selective State Space Model (Q-SSM), a hybrid quantum-optimized approach that integrates state space dynamics with a variational quantum gate. Instead of relying on expensive attention mechanisms, Q-SSM employs a simple parametrized quantum circuit (RY-RX ansatz) whose expectation values regulate memory updates adaptively. This quantum gating mechanism improves convergence stability, enhances the modeling of long-term dependencies, and provides a lightweight alternative to attention. We empirically validate Q-SSM on three widely used benchmarks, i.e., ETT, Traffic, and Exchange Rate. Results show that Q-SSM consistently improves over strong baselines (LSTM, TCN, Reformer), Transformer-based models, and S-Mamba. These findings demonstrate that variational quantum gating can address current limitations in long-range forecasting, leading to accurate and robust multivariate predictions.
Accurate state-of-health (SOH) estimation for lithium-ion batteries remains a challenging problem due to complex electrochemical degradation mechanisms and long-range temporal dependencies. In this work, we propose a quantum-enhanced recurrent framework, termed QLSTM, in which variational quantum circuits are directly embedded into the gating mechanisms of long short-term memory networks. By replacing classical affine transformations with parameterized unitary operations, the proposed model introduces structured nonlinear transformations into the recurrent state-transition process. Extensive experiments on multiple benchmark battery datasets demonstrate that QLSTM consistently outperforms classical sequence models in both predictive accuracy and robustness, achieving significant reductions in mean absolute error (MAE), with improvements on the order of 20% compared with classical LSTM baselines. Ablation studies further confirm that these improvements arise primarily from quantum-enhanced gating rather than input-level transformations. Additional analyses on qubit scaling and noise robustness reveal that model performance is governed by a balance between expressive capacity and trainability. These results provide empirical evidence that embedding quantum computational primitives within recurrent architectures offers a structurally grounded approach to improving sequence modeling capability. The proposed framework establishes a new design paradigm for integrating quantum operators into temporal learning models, with potential applications in complex dynamical system prediction tasks.
The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing the computational overhead. Self-attention integrates learnable query and key matrices to calculate attention scores between all pairs of tokens in a sequence. These scores are then multiplied by a learnable value matrix to obtain the output self-attention matrix, enabling the model to effectively capture long-range dependencies within the input sequence. Here, we propose a hybrid quantum-classical self-attention mechanism as part of a transformer decoder, the architecture underlying large language models (LLMs). To demonstrate its utility in chemistry, we train this model on the QM9 dataset for conditional generation, using SMILES strings as input, each labeled with a set of physicochemical properties that serve as conditions during inference. Our theoretical analysis shows that the time complexity of the query-key dot product is reduced from O ( n 2 d ) in a classical model to O ( n 2 log ⁡ d ) in our quantum model, where n and d represent the sequence length and the embedding dimension, respectively. We perform simulations using NVIDIA’s CUDA-Q platform, which is designed for efficient GPU scalability. This work provides a promising avenue for quantum-enhanced natural language processing (NLP).