相关论文: Let's Fuse Step by Step: A Generative Fusion Decod…

Federated learning faces critical challenges in balancing communication efficiency and model accuracy. One key issue lies in the approximation of update errors without incurring high computational costs. In this paper, we propose a…

While Large Language Models (LLMs) have shown remarkable abilities, they are hindered by significant resource consumption and considerable latency due to autoregressive processing. In this study, we introduce Adaptive N-gram Parallel…

The generation speed of LLMs are bottlenecked by autoregressive decoding, where tokens are predicted sequentially one by one. Alternatively, diffusion large language models (dLLMs) theoretically allow for parallel token generation, but in…

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the…

We introduce PGF-Net (Progressive Gated-Fusion Network), a novel deep learning framework designed for efficient and interpretable multimodal sentiment analysis. Our framework incorporates three primary innovations. Firstly, we propose a…

Code-switching (CS) speech refers to the phenomenon of mixing two or more languages within the same sentence. Despite the recent advances in automatic speech recognition (ASR), CS-ASR is still a challenging task ought to the grammatical…

Optical remote sensing imagery is indispensable for Earth observation, yet persistent cloud occlusion limits its downstream utility. Most cloud removal (CR) methods are optimized for low-level fidelity and can over-smooth textures and…

Most existing infrared-visible image fusion (IVIF) methods assume high-quality inputs, and therefore struggle to handle dual-source degraded scenarios, typically requiring manual selection and sequential application of multiple…

Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the…

In this paper, a new learning algorithm for Federated Learning (FL) is introduced. The proposed scheme is based on a weighted gradient aggregation using two-step optimization to offer a flexible training pipeline. Herein, two different…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

Semantic segmentation generates comprehensive understanding of scenes through densely predicting the category for each pixel. High-level features from Deep Convolutional Neural Networks already demonstrate their effectiveness in semantic…

In Open-domain Question Answering (ODQA), it is essential to discern relevant contexts as evidence and avoid spurious ones among retrieved results. The model architecture that uses concatenated multiple contexts in the decoding phase, i.e.,…

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs…

Modern vision-language models (VLMs) can act as generative OCR engines, yet open-ended decoding can expose rare but consequential failures. We identify a core deployment misalignment in generative OCR. Autoregressive decoding favors…

There has been significant progress in open-source text-only translation large language models (LLMs) with better language coverage and quality. However, these models can be only used in cascaded pipelines for speech translation (ST),…

Current Open-Domain Question Answering (ODQA) model paradigm often contains a retrieving module and a reading module. Given an input question, the reading module predicts the answer from the relevant passages which are retrieved by the…

Large language models (LLMs) exhibit complementary strengths arising from differences in pretraining data, model architectures, and decoding behaviors. Inference-time ensembling provides a practical way to combine these capabilities without…

The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs with datasets that necessitate domain-expert reasoning…

Retrieval-augmented generation (RAG) has emerged as a paradigm for grounding large language models in external knowledge, yet most existing RAG systems assume centralized knowledge access and ample computation. These assumptions break down…