相关论文: DK-Root: A Joint Data-and-Knowledge-Driven Framewo…

With the development of intelligent manufacturing and the increasing complexity of industrial production, root cause diagnosis has gradually become an important research direction in the field of industrial fault diagnosis. However,…

The Mixture-of-Experts (MoE) architecture has emerged as a powerful paradigm for scaling deep learning models, yet it is fundamentally limited by challenges such as expert imbalance and the computational complexity of classical routing…

Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance,…

DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of…

Emerging IoT applications are transitioning from battery-powered to grid-powered nodes. DRP, a contention-based data dissemination protocol, was developed for these applications. Traditional contention-based protocols resolve collisions…

Quality Estimation (QE) aims to assess the quality of machine translation (MT) outputs without relying on reference translations, making it essential for real-world, large-scale MT evaluation. Large Language Models (LLMs) have shown…

Mixture-of-Experts (MoE) architectures enable efficient scaling of large language models by activating only a subset of parameters per input. However, existing MoE models suffer from two critical limitations: (1) inefficient token-to-expert…

Deep learning-based diagnostic systems have demonstrated potential in skin disease diagnosis. However, their performance can easily degrade on test domains due to distribution shifts caused by input-level corruptions, such as imaging…

The determination of sample size in qualitative research has traditionally relied on the subjective and often ambiguous principle of data saturation, which can lead to inconsistencies and threaten methodological rigor. This study introduces…

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…

Class imbalance remains a critical challenge in machine learning (ML), particularly in the medical domain, where underrepresented minority classes lead to biased models and reduced predictive performance. This study introduces…

Most of the world's languages and dialects are low-resource, and lack support in mainstream machine translation (MT) models. However, many of them have a closely-related high-resource language (HRL) neighbor, and differ in linguistically…

5G wireless networks are complex, leveraging layers of scheduling, retransmission, and adaptation mechanisms to maximize their efficiency. But these mechanisms interact to produce significant fluctuations in uplink and downlink capacity and…

Imbalanced classification is a significant challenge in machine learning, especially in critical applications like medical diagnosis, fraud detection, and cybersecurity. Traditional oversampling techniques, such as SMOTE, often fail to…

Edge intelligence has emerged as a promising strategy to deliver low-latency and ubiquitous services for mobile devices. Recent advances in fine-tuning mechanisms of foundation models have enabled edge intelligence by integrating low-rank…

Marine obstacle detection demands robust segmentation under challenging conditions, such as sun glitter, fog, and rapidly changing wave patterns. These factors degrade image quality, while the scarcity and structural repetition of marine…

Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to do both retrieval over the full entity set and final decision making. We argue that this coupling is a core bottleneck: global high-recall search and…

Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through autoregressive…

Learning robot policies that capture multimodality in the training data has been a long-standing open challenge for behavior cloning. Recent approaches tackle the problem by modeling the conditional action distribution with generative…

Most unsupervised anomaly detection methods based on representations of normal samples to distinguish anomalies have recently made remarkable progress. However, existing methods only learn a single decision boundary for distinguishing the…