Related papers: FASTopic: Pretrained Transformer is a Fast, Adapti…

The dominant speech separation models are based on complex recurrent or convolution neural network that model speech sequences indirectly conditioning on context, such as passing information through many intermediate states in recurrent…

Topology optimization enables the design of highly efficient and complex structures, but conventional iterative methods, such as SIMP-based approaches, often suffer from high computational costs and sensitivity to initial conditions.…

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Dysarthric speech reconstruction (DSR) aims to convert dysarthric speech into comprehensible speech while maintaining the speaker's identity. Despite significant advancements, existing methods often struggle with low speech intelligibility…

Transient stability prediction is critically essential to the fast online assessment and maintaining the stable operation in power systems. The wide deployment of phasor measurement units (PMUs) promotes the development of data-driven…

A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embeddings can capture semantic relationship while semantically…

While speculative decoding has recently appeared as a promising direction for accelerating the inference of large language models (LLMs), the speedup and scalability are strongly bounded by the token acceptance rate. Prevalent methods…

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…

Transformer-based pre-trained models have achieved great improvements in semantic matching. However, existing models still suffer from insufficient ability to capture subtle differences. The modification, addition and deletion of words in…

Adapting pretrained multi-modal models to evolving test-time distributions, known as multi-modal test-time adaptation, presents a significant challenge. Existing methods frequently encounter negative transfer in the unbiased modality and…

Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Current approaches model…

Multi-node communication, which refers to the interaction among multiple devices, has attracted lots of attention in many Internet-of-Things (IoT) scenarios. However, its huge amounts of data flows and inflexibility for task extension have…

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…

Dysarthric speech reconstruction (DSR) typically employs a cascaded system that combines automatic speech recognition (ASR) and sentence-level text-to-speech (TTS) to convert dysarthric speech into normally-prosodied speech. However,…

Intelligent voice assistants, such as Apple Siri and Amazon Alexa, are widely used nowadays. These task-oriented dialogue systems require a semantic parsing module in order to process user utterances and understand the action to be…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Designing a fast and effective entropy model is challenging but essential for practical application of neural codecs. Beyond spatial autoregressive entropy models, more efficient backward adaptation-based entropy models have been recently…

Dialogue state tracking (DST) is an essential sub-task for task-oriented dialogue systems. Recent work has focused on deep neural models for DST. However, the neural models require a large dataset for training. Furthermore, applying them to…

The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR system remains a challenging task, requiring various resources,…

Topic modeling is a widely used technique for revealing underlying thematic structures within textual data. However, existing models have certain limitations, particularly when dealing with short text datasets that lack co-occurring words.…