Related papers: RAEE: A Robust Retrieval-Augmented Early Exit Fram…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

This paper presents EasyRAG, a simple, lightweight, and efficient retrieval-augmented generation framework for automated network operations. Our framework has three advantages. The first is accurate question answering. We designed a…

A network-based optimization approach, EEE, is proposed for the purpose of providing validation-viable state estimations to remediate the failure of pretrained models. To improve optimization efficiency and convergence, the most important…

Event extraction (EE) is a crucial research task for promptly apprehending event information from massive textual data. With the rapid development of deep learning, EE based on deep learning technology has become a research hotspot.…

Early-exit neural networks have become popular for reducing inference latency by allowing intermediate predictions when sufficient confidence is achieved. However, standard approaches typically rely on single-model confidence thresholds,…

We propose regular expression inference (REI) as a challenge for code/language modelling, and the wider machine learning community. REI is a supervised machine learning (ML) and program optimisation task, and poses the problem of finding…

Recently, deep neural networks have been outperforming conventional machine learning algorithms in many computer vision-related tasks. However, it is not computationally acceptable to implement these models on mobile and IoT devices and the…

Today, artificial neural networks are the state of the art for solving a variety of complex tasks, especially in image classification. Such architectures consist of a sequence of stacked layers with the aim of extracting useful information…

Convolutional neural networks (CNNs) have emerged as a powerful tool for automatic modulation classification (AMC) by directly extracting discriminative features from raw in-phase and quadrature (I/Q) signals. However, deploying CNN-based…

EIE proposed to accelerate pruned and compressed neural networks, exploiting weight sparsity, activation sparsity, and 4-bit weight-sharing in neural network accelerators. Since published in ISCA'16, it opened a new design space to…

We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input incrementally sentence-by-sentence while progressively…

Large reasoning models achieve strong performance on complex tasks by generating extended chains of thought, but they often "overthink": continuing to reason long after they have enough information to answer correctly. This wastes…

We introduce the \textit{Extract-Refine-Retrieve-Read} (ERRR) framework, a novel approach designed to bridge the pre-retrieval information gap in Retrieval-Augmented Generation (RAG) systems through query optimization tailored to meet the…

Early-exit deep neural networks enable adaptive inference by terminating computation when sufficient confidence is achieved, reducing cost for edge AI accelerators in resource-constrained settings. Existing methods, however, rely on…

Large language models (LLMs) demonstrate robust capabilities across diverse research domains. However, their performance in universal information extraction (UIE) remains insufficient, especially when tackling structured output scenarios…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

Student dropout in distance learning remains a critical challenge, with profound societal and economic consequences. While classical machine learning models leverage structured socio-demographic and behavioral data, they often fail to…

Deploying Large Language Model (LLM) applications, particularly those relying on Retrieval-Augmented Generation (RAG), remains challenging due to high computational demands, outdated knowledge bases, and the need to manually select optimal…

Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning…

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets.…