相关论文: QUADS: QUAntized Distillation Framework for Effici…

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Contemporary question answering (QA) systems, including transformer-based architectures, suffer from increasing computational and model complexity which render them inefficient for real-world applications with limited resources. Further,…

Dropout is a technique that silences the activity of units stochastically while training deep networks to reduce overfitting. Here we introduce Quantal Synaptic Dilution (QSD), a biologically plausible model of dropout regularisation based…

Edge devices operate in constrained and varying resource settings, requiring dynamic architectures that can adapt to limitations of the available resources. To meet such demands, layer dropping ($\mathcal{LD}$) approach is typically used to…

In spoken question answering, QA systems are designed to answer questions from contiguous text spans within the related speech transcripts. However, the most natural way that human seek or test their knowledge is via human conversations.…

Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…

One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment. While post-training compression methods are very popular, the question of obtaining…

Recent assertions of a potential advantage of Quantum Neural Network (QNN) for specific Machine Learning (ML) tasks have sparked the curiosity of a sizable number of application researchers. The parameterized quantum circuit (PQC), a major…

Previous chain-of-thought (CoT) distillation methods primarily focused on enhancing the reasoning capabilities of Small Language Models (SLMs) by utilizing high-quality rationales generated by powerful Large Language Models (LLMs, e.g.,…

3D semantic scene understanding is essential for digital twins, autonomous driving, smart agriculture, and embodied perception, yet dense point-wise annotation for point clouds remains expensive and difficult to scale. Existing…

Self-supervised learning (SSL) has achieved remarkable success across various speech-processing tasks. To enhance its efficiency, previous works often leverage the use of compression techniques. A notable recent attempt is DPHuBERT, which…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…

Self-supervised learning (SSL) has revolutionized audio representations, yet models often remain domain-specific, focusing on either speech or non-speech tasks. In this work, we present Universal Speech and Audio Distillation (USAD), a…

Despite the fact that data imbalance is becoming more and more common in real-world Spoken Language Understanding (SLU) applications, it has not been studied extensively in the literature. To the best of our knowledge, this paper presents…

This paper presents a comprehensive analysis of quantization techniques for optimizing Large Language Models (LLMs), specifically focusing on Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT). Through empirical…

Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable…

This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech…

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the current data distribution to the detriment of the past…