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

Source: [QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling](<https://www.sota2.com/research/paper/6a055731dbc836b87d828e4b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-15T05:00:12.430Z

Authors: Hoang-Quan Nguyen, Sankalp Pandey, Khoa Luu

Published: 2026-05-13T17:56:20.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on sMNIST](<https://www.sota2.com/research/sota/image-classification-on-smnist.md>): Image Classification; sMNIST; Fold 1 Performance Summary: 92.3.

- [Image Classification on sFashion-MNIST (10-Fold CV Results)](<https://www.sota2.com/research/sota/image-classification-on-sfashion-mnist-10-fold-cv-results.md>): Image Classification; sFashion-MNIST; Fold 1 Accuracy: 81.1.

- [Image Classification on sCIFAR-10 (10-Fold Cross-Validation)](<https://www.sota2.com/research/sota/image-classification-on-scifar-10-10-fold-cross-validation.md>): Image Classification; sCIFAR-10; Performance Metric (Fold 1): 53.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.13833>)

[PDF](<https://arxiv.org/pdf/2605.13833.pdf>)
