用量子门控提升Mamba模型的序列分类能力，实现更高效特征提取。
Hybrid Quantum-Classical Selective State Space Artificial Intelligence
- 将变分量子电路作为量子门控模块，增强特征提取与无关信息抑制
- 在重塑MNIST上4轮训练达24.6%准确率，优于纯经典方法的21.6%
- 适合追求低参数量、高表达力的轻量化大模型研究者
混合量子-经典（HQC）算法是利用量子系统计算优势解决大规模数值任务的有效范式。通过在高维希尔伯特空间中运行，量子线路可实现指数级加速，并提供比纯经典方法更丰富的代价景观表征。这一特性对机器学习尤为关键，因当前自然语言处理（NLP）模型受限于大规模矩阵乘法与高维优化带来的巨大时间复杂度。本文提出一种面向Mamba架构的混合量子-经典选择机制，专用于时序序列分类任务。该方法利用变分量子电路（VQCs）作为量子门控模块，同时增强特征提取与抑制无关信息的能力。此集成直接缓解深度学习架构的计算瓶颈，通过量子资源实现更高效的表示学习。我们分析了将量子子程序引入大语言模型（LLMs）对其泛化能力、表达力和参数效率的影响。结果表明，量子增强的门控机制是迈向可扩展、资源高效型NLP模型的重要路径，在有限模拟步数下表现显著。在重塑的MNIST数据集（输入格式为(batch, 784, d_model)）上，仅使用一个量子层的混合模型在前四轮训练中达到24.6%准确率，显著高于纯经典选择机制的21.6%。
原文摘要 · Abstract (English)
Hybrid Quantum Classical (HQC) algorithms constitute one of the most effective paradigms for exploiting the computational advantages of quantum systems in large-scale numerical tasks. By operating in high-dimensional Hilbert spaces, quantum circuits enable exponential speed-ups and provide access to richer representations of cost landscapes compared to purely classical methods. These capabilities are particularly relevant for machine learning, where state-of-the-art models especially in Natural Language Processing (NLP) suffer from prohibitive time complexity due to massive matrix multiplications and high-dimensional optimization. In this manuscript, we propose a Hybrid Quantum Classical selection mechanism for the Mamba architecture, designed specifically for temporal sequence classification problems. Our approach leverages Variational Quantum Circuits (VQCs) as quantum gating modules that both enhance feature extraction and improve suppression of irrelevant information. This integration directly addresses the computational bottlenecks of deep learning architectures by exploiting quantum resources for more efficient representation learning. We analyze how introducing quantum subroutines into large language models (LLMs) impacts their generalization capability, expressivity, and parameter efficiency. The results highlight the potential of quantum-enhanced gating mechanisms as a path toward scalable, resource-efficient NLP models, in a limited simulation step. Within the first four epochs on a reshaped MNIST dataset with input format (batch, 784, d_model), our hybrid model achieved 24.6% accuracy while using one quantum layer and achieve higher expressivity, compared to 21.6% obtained by a purely classical selection mechanism. we state No founding
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。