相关论文: DWTSumm: Discrete Wavelet Transform for Document S…

The digitalization of the legal domain has been ongoing for a couple of years. In that process, the application of different machine learning (ML) techniques is crucial. Tasks such as the classification of legal documents or contract…

In recent years, many research achievements are made in the medical image fusion field. Medical Image fusion means that several of various modality image information is comprehended together to form one image to express its information. The…

Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating specialized knowledge domains beyond their training…

In deep time series forecasting, the Fourier Transform (FT) is extensively employed for frequency representation learning. However, it often struggles in capturing multi-scale, time-sensitive patterns. Although the Wavelet Transform (WT)…

The exponential growth of online textual content across diverse domains has necessitated advanced methods for automated text classification. Large Language Models (LLMs) based on transformer architectures have shown significant success in…

This survey paper delves into the emerging and critical area of symbolic knowledge distillation in Large Language Models (LLMs). As LLMs like Generative Pre-trained Transformer-3 (GPT-3) and Bidirectional Encoder Representations from…

In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based…

The integration of extensive, dynamic knowledge into Large Language Models (LLMs) remains a significant challenge due to the inherent entanglement of factual data and reasoning patterns. Existing solutions, ranging from non-parametric…

Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient…

Denoising language models (DLMs) have been proposed as a powerful alternative to traditional language models (LMs) for automatic speech recognition (ASR), motivated by their ability to use bidirectional context and adapt to a specific ASR…

Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding space, so that images can be presented in essentially the…

Large Language Models (LLMs) have ushered in a new wave of artificial intelligence advancements impacting every scientific field and discipline. We live in a world where most of the data around us, e.g., text, audio, and music, has a…

Calculating semantic textual similarity is a foundational task in natural language processing. Current large language models (LLMs) based methods typically rely on extracting last-layer hidden states with fixed dimensions to compute…

While insights into the workings of the transformer model have largely emerged by analysing their behaviour on language tasks, this work investigates the representations learnt by the Vision Transformer (ViT) encoder through the lens of…

Transformer-based models have consistently produced substantial performance gains across a variety of NLP tasks, compared to shallow models. However, deep models are orders of magnitude more computationally expensive than shallow models,…

Existing approaches for low-resource text summarization primarily employ large language models (LLMs) like GPT-3 or GPT-4 at inference time to generate summaries directly; however, such approaches often suffer from inconsistent LLM outputs…

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and…

Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of…

Surface roughness and texture are critical to the functional performance of engineering components. The ability to analyze roughness and texture effectively and efficiently is much needed to ensure surface quality in many surface generation…

Existing Visual Speech Recognition (VSR) systems commonly rely on left-to-right autoregressive decoding, which can force premature decisions on visually ambiguous tokens before sufficient context is available. We propose DLLM-VSR, to the…