Skip to Content

428 Results Found

  • Article
  • Open Access
2,565 Views
9 Pages

20 October 2022

Natural language models brought rapid developments to Natural Language Processing (NLP) performance following the emergence of large-scale deep learning models. Language models have previously used token units to represent natural language while redu...

(This article belongs to the Special Issue Natural Language Processing (NLP) and Applications)
  • Article
  • Open Access
1 Citations
1,239 Views
35 Pages

16 January 2026

This paper is a theoretical contribution that introduces a new reasoning framework for SAT solving based on resolvable networks (RNs). RNs provide a graph-based representation of propositional satisfiability in which clauses are interpreted as direct...

(This article belongs to the Special Issue Graph Theory and Applications, 3rd Edition)
  • Article
  • Open Access
2 Citations
1,205 Views
33 Pages

12 March 2026

Emotions and affective responses are core intervention targets in music therapy. Through acoustic elements, music can evoke emotional responses at physiological and neurological levels, influencing cognition and behavior while providing an important...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
1 Citations
898 Views
24 Pages

26 May 2026

Large Language Models (LLMs) are typically safety-aligned using high-resource language data, but it remains unclear whether these constraints transfer reliably across distinct linguistic manifolds. This study examines the mathematical foundations of...

(This article belongs to the Special Issue Mathematical Foundations in NLP: Applications and Challenges)
  • Article
  • Open Access
5 Citations
1,313 Views
18 Pages

15 December 2025

Recent advancements in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing diverse data types, yet significant disparities persist between human cognitive processes and computational approaches to multimod...

  • Article
  • Open Access
6 Citations
8,235 Views
21 Pages

10 October 2020

From a social equality representation perspective, advertising should ideally mirror the multicultural composition at the national market, because mass-mediated identity representations may act as cultural resources for those with marginalised identi...

(This article belongs to the Special Issue Genealogies of Racial and Ethnic Representation)
  • Article
  • Open Access

18 November 2026

Ground-penetrating radar (GPR) inversion using deep learning may experience substantial performance degradation when acquisition parameters differ between training and testing. One important factor contributing to this sensitivity is the conventional...

(This article belongs to the Topic Ground Penetrating Radar (GPR) Techniques and Applications, 2nd Edition)
  • Article
  • Open Access
361 Views
23 Pages

GCGFormer: Geometry-Compatibility-Guided Attention for Rotated Object Detection

  • Huiji Wang,
  • Dandan Huang,
  • Zhi Liu,
  • Zhichao Han and ,
  • Yunhe Qiu and
  • Chunpeng Pan
  • + 1 author+ 0 author

22 September 2026

Rotated object detection in remote sensing imagery requires both semantic understanding and accurate geometric reasoning. Existing geometry-aware detectors commonly introduce geometric information through oriented proposals or decoder queries, making...

(This article belongs to the Special Issue Computer Vision and Sensors-Based Application for Intelligent Systems)
  • Article
  • Open Access
11 Citations
6,017 Views
12 Pages

It is important how the token unit is defined in a sentence in natural language process tasks, such as text classification, machine translation, and generation. Many studies recently utilized the subword tokenization in language models such as BERT,...

(This article belongs to the Special Issue Selected Papers from International Conference on Smart Media and Applications (SMA 2020))
  • Article
  • Open Access
133 Views
38 Pages

27 October 2026

Transformer-based analysis of physiological signals critically depends on how input tokens are constructed, yet conventional tokens derived from raw temporal windows or spectrogram patches may overlook the intrinsic oscillatory organization of electr...

  • Article
  • Open Access
389 Views
33 Pages

Saliency-Guided RT-DETR for Multi-Class Detection in Processing Tomato Sorting

  • Xingyu Jiang,
  • Yingjie Zhang,
  • Ximei Wei,
  • Xia Peng and
  • Weitao Chen

22 August 2026

This study considers multi-class visual detection for processing tomato sorting under controlled laboratory conditions. In densely arranged images, occlusion and visual similarity can weaken the local boundary and texture cues needed to distinguish r...

(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
  • Article
  • Open Access
2 Citations
5,213 Views
15 Pages

A Radical-Based Token Representation Method for Enhancing Chinese Pre-Trained Language Models

  • Honglun Qin,
  • Meiwen Li,
  • Lin Wang,
  • Youming Ge and ,
  • Junlong Zhu and
  • Ruijuan Zheng
  • + 1 author+ 0 author

In the domain of natural language processing (NLP), a primary challenge pertains to the process of Chinese tokenization, which remains challenging due to the lack of explicit word boundaries in written Chinese. The existing tokenization methods often...

  • Article
  • Open Access
2 Citations
995 Views
19 Pages

26 May 2025

The present study investigates the effects of token frequency, type frequency, and constituency on L2 compositional multiword sequence (CMS) processing among 60 Chinese L2 English speakers at two proficiency levels, using an online phrasal decision t...

(This article belongs to the Section Cognition)
  • Article
  • Open Access
10 Citations
3,487 Views
20 Pages

Bearing Fault Diagnosis Based on an Enhanced Image Representation Method of Vibration Signal and Conditional Super Token Transformer

  • Jiaying Li,
  • Han Liu,
  • Jiaxun Liang,
  • Jiahao Dong and ,
  • Bin Pang,
  • Ziyang Hao and
  • Xin Zhao
  • + 2 authors+ 0 author

31 July 2022

Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA) is an advanced deconvolution method, which can effectively inhibit the interference of background noise and distinguish the fault period by calculating the multipoint kurtosis values....

  • Article
  • Open Access
201 Views
69 Pages

22 October 2026

VibroAgent represented ten-second acceleration windows from one reference and five monitored locations as 84 continuous soft tokens for Gemma 4 E2B, letting one model decide and potentially explain; only its decisions were evaluated. Tasks were globa...

(This article belongs to the Special Issue AI in Complex Engineering Systems)
  • Article
  • Open Access
1 Citations
3,122 Views
9 Pages

Composing the representation of a sentence from the tokens that it comprises is difficult, because such a representation needs to account for how the words present relate to each other. The Transformer architecture does this by iteratively changing t...

(This article belongs to the Collection Natural Language Processing and Applications: Challenges and Perspectives)
  • Article
  • Open Access
33 Citations
13,634 Views
66 Pages

Extracting Sentence Embeddings from Pretrained Transformer Models

  • Lukas Stankevičius and
  • Mantas Lukoševičius

2 October 2024

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in retrieval-augmented gene...

(This article belongs to the Special Issue Advances in Large Language Models: Techniques, Applications and Challenges)
  • Article
  • Open Access
3 Citations
2,393 Views
18 Pages

26 November 2024

Video-based pedestrian re-identification (Re-ID) is used to re-identify the same person across different camera views. One of the key problems is to learn an effective representation for the pedestrian from video. However, it is difficult to learn an...

(This article belongs to the Special Issue Sensor-Based Behavioral Biometrics)
  • Article
  • Open Access
4 Citations
2,893 Views
30 Pages

Vision Transformers achieve strong performance across computer vision tasks but suffer from quadratic computational complexity with respect to token count, limiting deployment in resource-constrained environments. Existing token pruning methods rely...

(This article belongs to the Section Probability and Statistics)
  • Article
  • Open Access
536 Views
14 Pages

The subject of this paper is the problem of knowledge revealed by the emergence of advanced natural language processing technology, called large language models (LLMs). It proposes an interpretation of the appearance of this phenomenon as an emergent...

(This article belongs to the Special Issue Intelligent Inquiry into Intelligence)
  • Article
  • Open Access
1,195 Views
24 Pages

Spatial-Temporal Relation Enhancement for Speech Emotion Recognition from Acoustic Signals Using Fibonacci Encoding with Diverse Feature Fusion

  • Shicong Huang,
  • Jinghao Zhang,
  • Jingchao Xu,
  • Qi Zhang and ,
  • Zihan Li,
  • Songyang Wang,
  • Zirui Qiu,
  • Zijia Xiong,
  • Jintian Liang and
  • Changzeng Fu
  • + 5 authors+ 0 author

9 August 2026

Speech emotion recognition (SER) infers affective states from speech signals, but positional encoding for acoustic tokens remains underexplored in Transformer-based SER. Existing models often reuse encodings designed for text and do not explicitly ac...

(This article belongs to the Special Issue Applications of Sensors in Emotion Recognition)
  • Article
  • Open Access
4 Citations
2,518 Views
21 Pages

17 June 2025

Large pre-trained models (PLMs) have provided tremendous opportunities and potentialities for multimodal fake news detection. However, existing multimodal fake news detection methods never manipulate the token-wise hierarchical semantics of news yiel...

(This article belongs to the Special Issue Symmetries and Symmetry-Breaking in Data Security)
  • Article
  • Open Access
5 Citations
2,304 Views
13 Pages

13 August 2023

Named entity recognition involves two main types: nested named entity recognition and flat named entity recognition. The span-based approach treats nested entities and flat entities uniformly by classifying entities on a span representation. However,...

  • Article
  • Open Access
1,626 Views
16 Pages

15 July 2026

Real-world asset tokenization is often presented as a mechanism for improving the liquidity of traditionally illiquid assets. However, on-chain representation and secondary market liquidity are distinct outcomes. This paper examines observed liquidit...

(This article belongs to the Special Issue Cryptocurrency and Digital Cash)
  • Article
  • Open Access
1 Citations
2,481 Views
20 Pages

25 April 2025

Action representations are essential for developing mutual cognition toward efficient human–AI collaboration, particularly in human–robot collaborative (HRC) workspaces. As such, it has become an emerging research direction for robots to...

(This article belongs to the Special Issue Bayesian Learning and Its Advanced Applications)
  • Article
  • Open Access
89 Views
24 Pages

4 November 2026

Existing knowledge distillation methods for multimodal large language models (MLLMs) mainly align output distributions or intermediate representations, but rarely supervise how predictions depend on local visual evidence. This limitation may hinder t...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
2 Citations
2,106 Views
22 Pages

Probing the Topology of the Space of Tokens with Structured Prompts

  • Michael Robinson,
  • Sourya Dey and
  • Taisa Kushner

17 October 2025

Some large language models (LLMs) are open source and are therefore fully open for scientific study. However, many LLMs are proprietary, and their internals are hidden, which hinders the ability of the research community to study their behavior under...

(This article belongs to the Special Issue New Perspectives in Harmonic Analysis)
  • Article
  • Open Access
58 Citations
6,549 Views
22 Pages

Existing optical remote sensing image change detection (CD) methods aim to learn an appropriate discriminate decision by analyzing the feature information of bitemporal images obtained at the same place. However, the complex scenes in high-resolution...

  • Article
  • Open Access
267 Views
15 Pages

SFTINet: Spatial–Frequency Token Interaction for Multi-Modal Object Re-ID

  • Lin Qi,
  • Tiancun Guo,
  • Yanfei Dong,
  • Changbing Zheng and
  • Mingliang Gao

26 September 2026

Single-modal object Re-identification (Re-ID) frequently suffers from performance degradation under complex and dynamic scene conditions. Although multi-modal object Re-ID leverages complementary information across diverse modalities to alleviate thi...

(This article belongs to the Special Issue Recent Advances in Computer Vision: Technologies and Applications, 2nd Edition)
  • Article
  • Open Access
1 Citations
379 Views
24 Pages

26 September 2026

Radar emitter recognition based on pulse description words (PDWs) serves as a fundamental prerequisite for target identification and tracking in electronic support measures (ESM). Although self-supervised learning (SSL) has been widely applied to tex...

(This article belongs to the Section Radar Sensors)
  • Article
  • Open Access
828 Views
18 Pages

15 June 2026

Vision-and-language navigation (VLN) traditionally relies on explicit reasoning chains, which, despite being interpretable, impose severe constraints on inference efficiency and scalability in long-range environments. Existing multimodal large langua...

(This article belongs to the Section Navigation and Positioning)
  • Article
  • Open Access
546 Views
22 Pages

14 August 2026

Occluded person re-identification (Re-ID) is a challenging task, as non-target pedestrians or surrounding obstacles often interfere with the visual cues of the target person, making it difficult for models to effectively learn discriminative feature...

(This article belongs to the Section Internet of Things)
  • Article
  • Open Access
383 Views
9 Pages

Empirical 5/3 Spectral Scaling in Contextual Representations of Language

  • Zhongxin Yang,
  • Chun Bao,
  • Yuanwei Bin,
  • Xiang I. A. Yang and ,
  • Yipeng Shi and
  • Shiyi Chen
  • + 1 author+ 0 author

27 September 2026

Natural language is a complex system that exhibits robust statistical regularities. Here, we represent text as a trajectory in a high-dimensional embedding space generated by transformer-based language models, and quantify scale-dependent fluctuation...

(This article belongs to the Section Complexity)
  • Technical Note
  • Open Access
8 Citations
5,199 Views
17 Pages

20 October 2022

Automatic prediction of the plant and animal species most likely to be observed at a given geo-location is useful for many scenarios related to biodiversity management and conservation. However, the sparseness of aerial images results in small discre...

(This article belongs to the Special Issue Remote Sensing Applications in Vegetation Classification)
  • Article
  • Open Access
480 Views
29 Pages

Modulation-Prior Enhanced Cross-Modal Graph Learning for Low-SNR Automatic Modulation Recognition

  • Haibo Su,
  • Yixiang Luomei,
  • Zhentao Yang,
  • Feiyu Mou and ,
  • Zhenghong Lu and
  • Yi Chen
  • + 1 author+ 0 author

17 September 2026

Automatic modulation recognition (AMR) is a key enabling technique for intelligent spectrum sensing, non-cooperative wireless signal analysis, and communication monitoring. However, its reliability degrades significantly under low signal-to-noise rat...

(This article belongs to the Section Remote Sensors)
  • Article
  • Open Access
803 Views
19 Pages

STAGE: LLM-Driven Semantic and Topological Augmented Graph Embedding for Text-Attributed Graphs

  • Shiwei Huang,
  • Shunxin Xiao,
  • Xu-Yao Zhang,
  • Shunzhi Zhu and ,
  • Luoqi Liu and
  • Da-Han Wang
  • + 1 author+ 0 author

Text-attributed graphs (TAGs) require models to jointly exploit node text and graph structure, yet doing so effectively remains difficult when node text is sparse and the structural context is large. Here, we propose STAGE (Semantic and Topological A...

(This article belongs to the Special Issue Causal Inference and Machine Learning: Mathematical Modeling, Analysis and Applications)
  • Article
  • Open Access
1,016 Views
25 Pages

24 May 2026

While Vision Transformers (ViTs) have achieved state-of-the-art (SOTA) results in visual recognition, their scalability remains fundamentally constrained by the quadratic complexity of global self-attention. To address this, we present a linear compl...

  • Article
  • Open Access
8 Citations
4,404 Views
18 Pages

27 March 2024

Medical imaging description and disease diagnosis are vitally important yet time-consuming. Automated diagnosis report generation (DRG) from medical imaging description can reduce clinicians’ workload and improve their routine efficiency. To ad...

(This article belongs to the Special Issue Applications, Challenges and Future Direction of Natural Language Processing Based on Deep Learning)
  • Article
  • Open Access
368 Views
41 Pages

Digital Transformer for Fracture Classification: SYM-Fractron, a Physics-Driven Hybrid Binary–Symbolic Computing Ecosystem

  • Klaudia Oleshko,
  • María de Jesús Correa López,
  • Andrey Khrennikov,
  • Qiuming Cheng and ,
  • José Luis Landa,
  • Ramiro Guillermo Paz Cruz,
  • Alejandro Romero,
  • Paulina Patiño and
  • Yesica Guerrero Amador
  • + 4 authors+ 0 author

Fracture networks control fluid flow, reservoir connectivity, and production performance in carbonate systems, yet their multiscale hierarchical organization remains difficult to characterize from heterogeneous geological and geophysical datasets. He...

(This article belongs to the Special Issue Fractional and Fractal Methods with Their Mechanics Applications)
  • Article
  • Open Access
5 Citations
2,441 Views
23 Pages

D2Former: Dual-Domain Transformer for Change Detection in VHR Remote Sensing Images

  • Huanhuan Zheng,
  • Hui Liu,
  • Lei Lu,
  • Shiyin Li and
  • Jiyan Lin

Computational intelligence technologies have been extensively applied for the interpretation of remote sensing imagery. Recently, the computational-intelligence-based Transformer change detection (CD) approach has attracted increasing attention. Howe...

(This article belongs to the Topic Computational Intelligence in Remote Sensing: 2nd Edition)
  • Article
  • Open Access
9 Citations
3,283 Views
25 Pages

19 May 2025

Threat intelligence is crucial for the early detection of network security threats, and named entity recognition (NER) plays a critical role in this process. However, traditional NER models based on sequence tagging primarily focus on word-level info...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
21 Citations
4,139 Views
20 Pages

Methodology for Assessing the Digital Image of an Enterprise with Its Industry Specifics

  • Dmitriy Rodionov,
  • Darya Kryzhko,
  • Timur Tenishev,
  • Victor Uimanov and ,
  • Alsu Abdulmanova,
  • Ani Kvikviniia,
  • Pavel Aksenov,
  • Mark Solovyov,
  • Fedor Kolomenskii and
  • Evgenii Konnikov
  • + 5 authors+ 0 author

24 May 2022

This study provides a framework for the comparative assessment of the key industry aspects of competitiveness among logistics services and the logistics systems of enterprises in the informational environment. Frequently, the relationships between a...

  • Article
  • Open Access
727 Views
25 Pages

15 May 2026

Music emotion recognition (MER) can be formulated as a multimodal optimization problem that predicts an emotion label from coupled audio and lyric sequences. Existing methods typically perform unimodal learning or coarse global fusion, which overlook...

(This article belongs to the Special Issue Intelligent Mathematics and Applications)
  • Article
  • Open Access
2 Citations
2,942 Views
17 Pages

Statement-Grained Hierarchy Enhanced Code Summarization

  • Qianjin Zhang,
  • Dahai Jin,
  • Yawen Wang and
  • Yunzhan Gong

15 February 2024

Code summarization plays a vital role in aiding developers with program comprehension by generating corresponding textual descriptions for code snippets. While recent approaches have concentrated on encoding the textual and structural characteristics...

(This article belongs to the Special Issue Advances in Software Engineering and Programming Languages)
  • Article
  • Open Access
356 Views
25 Pages

Language Model-Aided Text Semantic Communications for Digital-Twin Interaction

  • Bo Chen,
  • Can Wang,
  • Xinguo Chen,
  • Shuai Zhang and ,
  • Huachun Tan and
  • Liting Zhang
  • + 1 author+ 0 author

29 September 2026

Reliable semantic interaction between physical entities and their virtual counterparts is fundamental to digital-twin operation. In challenging wireless environments, however, channel noise and fading corrupt continuous semantic representations, caus...

(This article belongs to the Section Microwave and Wireless Communications)
  • Article
  • Open Access
177 Views
13 Pages

VBT-Fusion: Branch-Selective Language Conditioning for Infrared–Visible Image Fusion

  • Jie Ma,
  • Shubao Pan,
  • Xi Shao,
  • Yongjun Wang and
  • Shaorong Zhang

12 October 2026

Infrared–visible image fusion must reconcile different sensor roles: infrared imagery provides illumination-robust thermal evidence, whereas visible imagery supplies richer but illumination-sensitive structures and textures. Existing vision&nda...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
41 Citations
6,301 Views
13 Pages

An ERNIE-Based Joint Model for Chinese Named Entity Recognition

  • Yu Wang,
  • Yining Sun,
  • Zuchang Ma,
  • Lisheng Gao and
  • Yang Xu

18 August 2020

Named Entity Recognition (NER) is the fundamental task for Natural Language Processing (NLP) and the initial step in building a Knowledge Graph (KG). Recently, BERT (Bidirectional Encoder Representations from Transformers), which is a pre-training mo...

(This article belongs to the Special Issue Machine Learning and Natural Language Processing)
  • Article
  • Open Access
1 Citations
486 Views
33 Pages

3 July 2026

Deep learning methods that integrate convolutional neural networks (CNNs) and Transformers have achieved remarkable progress in hyperspectral image (HSI) classification. However, existing methods still suffer from insufficient multi-scale spatial&nda...

  • Article
  • Open Access
451 Views
25 Pages

24 August 2026

Background: Major depressive disorder (MDD) is a common psychiatric disorder. Electroencephalography (EEG) provides physiological information for depression detection, but many existing methods rely on dense multichannel recordings, limiting their us...

(This article belongs to the Section Neurotechnology and Neuroimaging)
  • Article
  • Open Access
1,131 Views
23 Pages

Debiased Multiplex Tokenization Using Mamba-Based Pointers for Efficient and Versatile Map-Free Visual Relocalization

  • Wenshuai Wang,
  • Hong Liu,
  • Shengquan Li,
  • Peifeng Jiang and ,
  • Dandan Che and
  • Runwei Ding
  • + 1 author+ 0 author

Visual localization plays a critical role for mobile robots to estimate their position and orientation in GPS-denied environments. However, its efficiency, robustness, and generalization are fundamentally undermined by severe viewpoint changes and dr...

of 9