相关论文: SAP: Syntactic Attention Pruning for Transformer-b…

Although large-scale self-supervised learning (SSL) models like WavLM have achieved state-of-the-art performance in speech processing, their significant size impedes deployment on resource-constrained devices. While structured pruning is a…

We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual cortex does not…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

Autoregressive Transformers adopted in Large Language Models (LLMs) are hard to scale to long sequences. Despite several works trying to reduce their computational cost, most of LLMs still adopt attention layers between all pairs of tokens…

In an enterprise Virtual Assistant (VA) system, intent classification is the crucial component that determines how a user input is handled based on what the user wants. The VA system is expected to be a cost-efficient SaaS service with low…

Network Pruning is a promising way to address the huge computing resource demands of the deployment and inference of Large Language Models (LLMs). Retraining-free is important for LLMs' pruning methods. However, almost all of the existing…

Advances in language modeling have led to the development of deep attention-based models that are performant across a wide variety of natural language processing (NLP) problems. These language models are typified by a pre-training process…

Speech separation (SS) seeks to disentangle a multi-talker speech mixture into single-talker speech streams. Although SS can be generally achieved using offline methods, such a processing paradigm is not suitable for real-time streaming…

Multi-head self-attention is a key component of the Transformer, a state-of-the-art architecture for neural machine translation. In this work we evaluate the contribution made by individual attention heads in the encoder to the overall…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Transformer models have achieved superior performance in various natural language processing tasks. However, the quadratic computational cost of the attention mechanism limits its practicality for long sequences. There are existing…

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…

Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…

Transformer-based deep neural networks have achieved great success in various sequence applications due to their powerful ability to model long-range dependency. The key module of Transformer is self-attention (SA) which extracts features…

Autonomous driving systems rely on panoptic perception to jointly handle object detection, drivable area segmentation, and lane line segmentation. Although multi-task learning is an effective way to integrate these tasks, its increasing…

Spiking neural networks (SNNs), recognized as an energy-efficient alternative to traditional artificial neural networks (ANNs), have advanced rapidly through the scaling of models and datasets. However, such scaling incurs considerable…

Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs…

Multi-turn response selection is a challenging task due to its high demands on efficient extraction of the matching features from abundant information provided by context utterances. Since incorporating syntactic information like dependency…

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and…

Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization. To address this,…