Related papers: Blending Complementary Memory Systems in Hybrid Qu…

The emergence of Phase-Change Memory (PCM) provides opportunities for directly connecting persistent memory to main memory bus. While PCM achieves high read throughput and low standby power, the critical concerns are its poor write…

KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve…

Transformers' quadratic computational complexity limits their scalability despite remarkable performance. While linear attention reduces this to linear complexity, pre-training such models from scratch remains, in most cases, prohibitively…

Federated Learning (FL) enables multiple clients to collaboratively train a shared model while preserving data privacy. However, the high memory demand during model training severely limits the deployment of FL on resource-constrained…

We propose a simplified model of attention which is applicable to feed-forward neural networks and demonstrate that the resulting model can solve the synthetic "addition" and "multiplication" long-term memory problems for sequence lengths…

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

We present Federated QT-LSTM, a novel framework that combines the Quantum-Train (QT) methodology with Long Short-Term Memory (LSTM) networks in a federated learning setup. By leveraging quantum neural networks (QNNs) to generate classical…

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT…

Transformers have become the de facto architecture for a wide range of machine learning tasks, particularly in large language models (LLMs). Despite their remarkable performance, many challenges remain in training deep transformer networks,…

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Large Language Models (LLMs) are powerful but incur high memory and computation costs. Quantization is an effective solution, with INT weights and FP activations being widely adopted to preserve accuracy. Prior works further reduce FP…

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…

Hybrid quantum-classical models represent a crucial step toward leveraging near-term quantum devices for sequential data processing. We present Quantum Recurrent Neural Networks (QRNNs) and Quantum Convolutional Neural Networks (QCNNs) as…

Training machine learning models in an incremental fashion is not only important but also an efficient way to achieve artificial general intelligence. The ability that humans possess of continuous or lifelong learning helps them to not…

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing a vertically chunked…

This paper develops a memory-efficient approach for Sequential Pattern Mining (SPM), a fundamental topic in knowledge discovery that faces a well-known memory bottleneck for large data sets. Our methodology involves a novel hybrid trie data…

The Transformer model has been pivotal in advancing fields such as natural language processing, speech recognition, and computer vision. However, a critical limitation of this model is its quadratic computational and memory complexity…

It has been shown that semi-parametric methods, which combine standard neural networks with non-parametric components such as external memory modules and data retrieval, are particularly helpful in data scarcity and out-of-distribution…

We propose how to realize high-fidelity quantum storage using a hybrid quantum architecture including two coupled flux qubits and a nitrogen-vacancy center ensemble (NVE). One of the flux qubits is considered as the quantum computing…

Machine Learning algorithms based on Brain-inspired Hyperdimensional(HD) computing imitate cognition by exploiting statistical properties of high-dimensional vector spaces. It is a promising solution for achieving high energy efficiency in…