Related papers: Ultra-Lightweight Speech Separation via Group Comm…

This paper presents novel systems and methodologies for the development of efficient large language models (LLMs). It explores the trade-offs between model size, performance, and computational resources, with the aim of maximizing the…

Given the increasing demand from wireless applications, designing energy-efficient group communication protocols is of great importance to multi-hop wireless networks. A group communication session involves a set of member nodes, each of…

A relatively simple low complexity multiuser communication system based on simultaneous code and frequency index modulation (CFIM) is proposed in this paper. The proposed architecture reduces the emitted energy at the transmitter as well as…

Recently, diffusion models (DMs) have been increasingly used in audio processing tasks, including speech super-resolution (SR), which aims to restore high-frequency content given low-resolution speech utterances. This is commonly achieved…

The rapid development of generative Artificial Intelligence (AI) continually unveils the potential of Semantic Communication (SemCom). However, current talking-face SemCom systems still encounter challenges such as low bandwidth…

Deploying Large Language Models (LLMs) on edge or mobile devices offers significant benefits, such as enhanced data privacy and real-time processing capabilities. However, it also faces critical challenges due to the substantial memory…

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation…

While speech Large Language Models (LLMs) excel at conventional tasks like basic speech recognition, they lack fine-grained, multi-dimensional perception. This deficiency is evident in their struggle to disentangle complex features like…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…

Deploying Large Language Models (LLMs) on edge devices enhances privacy but faces performance hurdles due to limited resources. We introduce a systematic methodology to evaluate on-device LLMs, balancing capability, efficiency, and resource…

Large language models (LLMs) have revolutionized numerous applications, yet their deployment remains challenged by memory constraints on local devices. While scaling laws have enhanced LLM capabilities, the primary bottleneck has shifted…

The effective incorporation of cross-utterance information has the potential to improve language models (LMs) for automatic speech recognition (ASR). To extract more powerful and robust cross-utterance representations for the Transformer LM…

While large models have achieved significant progress in computer vision, challenges such as optimization complexity, the intricacy of transformer architectures, computational constraints, and practical application demands highlight the…

Training large language models is generally done via optimization methods on clusters containing tens of thousands of accelerators, communicating over a high-bandwidth interconnect. Scaling up these clusters is expensive and can become…

Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…

Medical image segmentation plays a pivotal role in disease diagnosis and treatment planning, particularly in resource-constrained clinical settings where lightweight and generalizable models are urgently needed. However, existing…

Effective patient-provider communication is difficult to assess at scale. We examine whether large language models (LLMs) can track 20 social behaviors from clinical transcripts without fine-tuning. Across three model families and multiple…

Ensembles of generative large language models (LLMs) are a promising way to compensate for individual model limitations, integrating the strengths of different LLMs. Existing LLM ensemble methods, however, face limitations such as…

Large language models (LLM) have achieved remarkable performance across a wide range of tasks. However, their substantial parameter sizes pose significant challenges for deployment on edge devices with limited computational and memory…

Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integration into various systems. Many such NLP systems, including…