Skip to Content

163 Results Found

  • Proceeding Paper
  • Open Access
137 Views
8 Pages

Improving Logical Reasoning of Small-Scale Language Models

  • Yusei Kimura,
  • Kazunori Komatani and
  • Masayuki Numao

26 October 2026

To improve the inference performance of small-scale language models, we proposed a stepwise phased process design that divides problem-solving into multiple phases and evaluated it using the Grade School Math 8K arithmetic word problem dataset. We ad...

  • Article
  • Open Access
3 Citations
3,777 Views
14 Pages

25 February 2025

Grammatical error correction (GEC) has become increasingly important for enhancing the quality of OCR-scanned texts. This small-scale study explores the application of Large Language Models (LLMs) for GEC in German children’s literature, a genr...

(This article belongs to the Special Issue Applications of Natural Language Processing to Data Science)
  • Article
  • Open Access
18 Citations
9,814 Views
21 Pages

Low-resource languages remain underserved by contemporary large language models (LLMs) because they lack sizable corpora, bespoke preprocessing tools, and the computing budgets assumed by mainstream alignment pipelines. Focusing on Kazakh, we present...

  • Article
  • Open Access
4,411 Views
12 Pages

29 December 2019

To overcome the data sparseness in word embedding trained in low-resource languages, we propose a punctuation and parallel corpus based word embedding model. In particular, we generate the global word-pair co-occurrence matrix with the punctuation-ba...

(This article belongs to the Special Issue Computational Linguistics for Low-Resource Languages)
  • Article
  • Open Access
1,135 Views
30 Pages

Agentic AI-Driven Cultivation Advisory and Symptom-Level Diagnostic Support in a Controlled Indoor Farming System

  • Jutarut Chaoraingern,
  • Akarat Pattaraanuvong,
  • Kantapon Paraksa,
  • Kantiporn Khunthong and ,
  • Tirawat Nontiwantok and
  • Arjin Numsomran
  • + 1 author+ 0 author

Small-scale and urban indoor farms typically rely on manual observation, which delays stress detection and yields inconsistent crop quality. While large language models (LLMs) and retrieval-augmented generation (RAG) have been explored for agricultur...

  • Article
  • Open Access
2 Citations
2,872 Views
21 Pages

3 September 2022

Some neural models achieve outstanding results in image recognition, semantic segmentation and natural language processing. However, their classification performance on structured and small-scale datasets that do not involve feature extraction is wor...

(This article belongs to the Section Computational Neuroscience, Neuroinformatics, and Neurocomputing)
  • Article
  • Open Access
1 Citations
2,573 Views
17 Pages

20 July 2024

This article presents a transfer-learning-based method to improve the synthesized speech quality of the low-resource Dungan language. This improvement is accomplished by fine-tuning a pre-trained Mandarin acoustic model to a Dungan language acoustic...

(This article belongs to the Special Issue Computational Linguistics: From Text to Speech Technologies)
  • Article
  • Open Access
9 Citations
5,327 Views
15 Pages

Military Equipment Entity Extraction Based on Large Language Model

  • Xuhong Liu,
  • Zhipeng Yu,
  • Xiulei Liu,
  • Lin Miao and
  • Tao Yang

8 October 2024

The technology of military equipment entity extraction, a crucial component in constructing military knowledge bases, holds significant research value and theoretical importance for guiding the development and improvement of equipment support forces....

  • Article
  • Open Access
4 Citations
2,001 Views
30 Pages

13 March 2026

How closely do the subjective perceptions simulated by Artificial Intelligence align with the subjective perceptions of human participants when evaluating an urban environment? This study serves as a pilot investigation to explore how far multimodal...

  • Technical Note
  • Open Access
9 Citations
4,635 Views
32 Pages

1 July 2024

In the field of Natural Language Processing (NLP), the lack of support for minority languages, especially Uyghur, the scarcity of Uyghur language corpora in the agricultural domain, and the lightweight nature of large language models remain prominent...

(This article belongs to the Topic Theoretical and Applied Problems in Human-Computer Intelligent Systems)
  • Communication
  • Open Access
1 Citations
741 Views
20 Pages

Consistency-Guided Distillation from Vision Foundation Models for Zero-Shot Airborne Point Cloud Segmentation

  • Yuan Gao,
  • Jindong Zhao,
  • Shaobo Xia,
  • Sheng Nie and ,
  • Cheng Wang and
  • Xiaohuan Xi
  • + 1 author+ 0 author

6 June 2026

Semantic segmentation of large-scale airborne point clouds traditionally relies on labor-intensive 3D manual annotations. While recent zero-shot methods attempt to alleviate this burden by distilling knowledge from 2D Vision–Language Models (VL...

(This article belongs to the Section AI Remote Sensing)
  • Article
  • Open Access
14 Citations
5,861 Views
14 Pages

Using Augmented Small Multimodal Models to Guide Large Language Models for Multimodal Relation Extraction

  • Wentao He,
  • Hanjie Ma,
  • Shaohua Li,
  • Hui Dong and ,
  • Haixiang Zhang and
  • Jie Feng
  • + 1 author+ 0 author

10 November 2023

Multimodal Relation Extraction (MRE) is a core task for constructing Multimodal Knowledge images (MKGs). Most current research is based on fine-tuning small-scale single-modal image and text pre-trained models, but we find that image-text datasets fr...

(This article belongs to the Topic Advances in Artificial Neural Networks)
  • Article
  • Open Access
6 Citations
3,937 Views
20 Pages

26 September 2025

In recent years, methods that selectively fine-tune or reduce the number of layers in large language models (LLMs) have garnered attention as an efficient alternative to traditional fine-tuning, where all layers are trained. In this study, we revisit...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
3 Citations
3,311 Views
19 Pages

23 July 2025

Text2Cypher is a text-to-text task that converts natural language questions into Cypher queries. Recent research by Neo4j on Text2Cypher demonstrates that fine-tuning a baseline language model (a pretrained and instruction-tuned generative model) usi...

  • Article
  • Open Access
397 Views
20 Pages

29 May 2026

To address the problems of the limited feature extraction capability and insufficient training efficiency of the traditional Continuous Bag-of-Words (CBOW) model in Natural Language Processing (NLP), the Quantum Neural Network-enhanced CBOW model (QN...

(This article belongs to the Special Issue Quantum Algorithms and Quantum Machine Learning)
  • Article
  • Open Access
2 Citations
1,040 Views
23 Pages

14 April 2026

To deal with the high standards, strong restrictions, and high repeatability that are inside State Grid small-scale infrastructure projects, this research puts forward a norm-driven generative design method, which conquers the low efficiency, complia...

(This article belongs to the Section Civil Engineering)
  • Article
  • Open Access
5 Citations
3,331 Views
19 Pages

Construction of an Online Cloud Platform for Zhuang Speech Recognition and Translation with Edge-Computing-Based Deep Learning Algorithm

  • Zeping Fan,
  • Min Huang,
  • Xuejun Zhang,
  • Rongqi Liu and ,
  • Xinyi Lyu,
  • Taisen Duan,
  • Zhaohui Bu and
  • Jianghua Liang
  • + 3 authors+ 0 author

9 November 2023

The Zhuang ethnic minority in China possesses its own ethnic language and no ethnic script. Cultural exchange and transmission encounter hurdles as the Zhuang rely exclusively on oral communication. An online cloud-based platform was required to enha...

(This article belongs to the Topic Electronic Communications, IOT and Big Data)
  • Feature Paper
  • Article
  • Open Access
16 Citations
11,167 Views
16 Pages

The Geometry of Concepts: Sparse Autoencoder Feature Structure

  • Yuxiao Li,
  • Eric J. Michaud,
  • David D. Baek,
  • Joshua Engels and ,
  • Xiaoqing Sun and
  • Max Tegmark
  • + 1 author+ 0 author

27 March 2025

Sparse autoencoders have recently produced dictionaries of high-dimensional vectors corresponding to the universe of concepts represented by large language models. We find that this concept universe has interesting structure at three levels: (1) The...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
2 Citations
1,921 Views
32 Pages

Knowledge-Driven Generative Design of Role-Playing Game Scenarios

  • Wojciech Owczarek,
  • Julia Wróbel and
  • Damian Pęszor

19 March 2026

The paper addresses the problem of the generative creation of role-playing game scenarios based on a knowledge compendium. The purpose of this exploratory research was to determine the impact of elements of the generation process on the quality of th...

(This article belongs to the Special Issue Applications of Deep Learning and Generative AI Models: Challenges and Opportunities)
  • Article
  • Open Access
4 Citations
3,708 Views
21 Pages

13 August 2025

This study introduces the concept of symmetry as a fundamental theoretical perspective for understanding the linguistic structure of cyberbullying texts. It posits that such texts often exhibit symmetry breaking between surface-level language forms a...

(This article belongs to the Section A: Computer Science)
  • Article
  • Open Access
6 Citations
3,448 Views
21 Pages

4 June 2024

In the transition from television to mobile devices, short videos have emerged as the primary content format, possessing tremendous potential in various fields such as marketing, promotion, education, advertising, and so on. However, from the availab...

(This article belongs to the Special Issue Knowledge and Data Engineering)
  • Article
  • Open Access
2 Citations
1,458 Views
20 Pages

The rise of Online Social Networks has reshaped global discourse, enabling real-time conversations on complex issues such as irregular migration. Yet the informal, multilingual, and often noisy nature of content on platforms like X (formerly Twitter)...

(This article belongs to the Special Issue Artificial Intelligence-Driven Emerging Applications)
  • Article
  • Open Access
841 Views
23 Pages

Accelerated LLM: A Fuzzy-Logic-Augmented Router Architecture for Efficient Multi-Domain Query Processing via Specialised Small Language Models

  • Kushagra Agrawal,
  • Deshmukh Nirmiti Akshay,
  • Palak Kaushik,
  • Shaveta Jain and ,
  • Ganga Sharma and
  • Sumendra Yogarayan
  • + 1 author+ 0 author

Large language models (LLMs) incur prohibitive computational costs when deployed as monolithic systems for multi-domain query processing. This paper proposes Accelerated LLM, a modular architecture that replaces a single general-purpose LLM with an e...

(This article belongs to the Topic Applications of NLP, AI, and ML in Software Engineering)
  • Article
  • Open Access
12 Citations
6,666 Views
22 Pages

Attention-Based Transformer-BiGRU for Question Classification

  • Dongfang Han,
  • Turdi Tohti and
  • Askar Hamdulla

20 April 2022

A question answering (QA) system is a research direction in the field of artificial intelligence and natural language processing (NLP) that has attracted much attention and has broad development prospects. As one of the main components in the QA syst...

(This article belongs to the Topic Data Science and Knowledge Discovery)
  • Article
  • Open Access
23 Citations
12,138 Views
25 Pages

23 February 2022

Abstractive summarization is a technique that allows for extracting condensed meanings from long texts, with a variety of potential practical applications. Nonetheless, today’s abstractive summarization research is limited to testing the models...

(This article belongs to the Special Issue Selected Papers from the 9th Annual Conference "Comparative Media Studies in Today's World" (CMSTW'2021))
  • Article
  • Open Access
2,067 Views
19 Pages

A Lightweight AI System to Generate Headline Messages for Inventory Status Summarization

  • Bongjun Ji,
  • Yukwan Hwang,
  • Donghun Kim,
  • Jungmin Park and ,
  • Minhyeok Ryu and
  • Yongkyu Cho
  • + 1 author+ 0 author

26 August 2025

In the manufacturing supply chain, management reports often begin with concise messages that summarize key inventory insights. Traditionally, human analysts manually crafted these summary messages by sifting through complex data—a process that...

(This article belongs to the Special Issue Data-Driven Analysis of Industrial Systems Using AI)
  • Article
  • Open Access
4 Citations
2,116 Views
13 Pages

MHlinker: Research on a Joint Extraction Method of Fault Entity Relationship for Mine Hoist

  • Xiaochao Dang,
  • Han Deng,
  • Xiaohui Dong,
  • Zhongyan Zhu and ,
  • Fenfang Li and
  • Li Wang
  • + 1 author+ 0 author

14 August 2023

Triplet extraction is the key technology to automatically construct knowledge graphs. Extracting the triplet of mechanical equipment fault relationships is of great significance in constructing the fault diagnosis of a mine hoist. The pipeline triple...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
5 Citations
2,208 Views
25 Pages

RQ-OSPTrans: A Semantic Classification Method Based on Transformer That Combines Overall Semantic Perception and “Repeated Questioning” Learning Mechanism

  • Yuanjun Tan,
  • Quanling Liu,
  • Tingting Liu,
  • Hai Liu and ,
  • Shengming Wang and
  • Zengzhao Chen
  • + 1 author+ 0 author

17 May 2024

The pre-trained language model based on Transformers possesses exceptional general text-understanding capabilities, empowering it to adeptly manage a variety of tasks. However, the topic classification ability of the pre-trained language model will b...

  • Article
  • Open Access
1 Citations
3,632 Views
14 Pages

22 September 2024

In general, it is difficult to obtain a huge, labeled dataset for deep learning-based phoneme recognition in singing voices. Studying singing voices also offers inherent challenges, compared to speech, because of the distinct variations in pitch, dur...

  • Article
  • Open Access
3,116 Views
13 Pages

Improving Computation Time for Optimization Runs of Modelica-Based Energy Systems

  • Sven Klute,
  • Markus Hadam,
  • Mathias van Beek and
  • Marcus Budt

2 January 2024

Mathematical optimization is a widespread method in order to improve, for instance, the efficiency of energy systems. A simulation approach based on partial differential equations can typically not be formulated as an optimization problem, thus requi...

(This article belongs to the Topic Advances in Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems from ECOS 2023)
  • Article
  • Open Access
15 Citations
5,877 Views
28 Pages

SecureLLM: A Unified Framework for Privacy-Focused Large Language Models

  • Konstantinos Kalodanis,
  • Sotirios Papadopoulos,
  • Georgios Feretzakis,
  • Panagiotis Rizomiliotis and
  • Dimosthenis Anagnostopoulos

10 April 2025

Large language models (LLMs) have shown remarkable skills across various activities, including text generation and code synthesis. Their widespread applicability, however, raises substantial concerns about security, privacy, and possibly misuse. Of r...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
15 Citations
3,368 Views
24 Pages

Cotton leaf disease detection is essential for accurate identification and timely management of diseases. It plays a crucial role in enhancing cotton yield and quality while promoting the advancement of intelligent agriculture and efficient crop harv...

(This article belongs to the Section Artificial Intelligence and Digital Agriculture)
  • Article
  • Open Access
455 Views
25 Pages

4 October 2026

In higher education, hallucination-free information retrieval is critical for navigating complex institutional legislation. This study develops a highly accurate, production-ready Retrieval-Augmented Generation (RAG) architecture tailored to Turkish,...

(This article belongs to the Special Issue Symmetry and Asymmetry in Natural Language Processing)
  • Article
  • Open Access
435 Views
34 Pages

19 September 2026

Remote sensing referring image segmentation faces critical challenges including arbitrary target rotation, drastic scale variation, cluttered complex backgrounds, and large visual-language semantic gaps. Existing mainstream segmentation models adopt...

(This article belongs to the Special Issue Unified and Multimodal Segmentation: Foundations, Methods, and Applications)
  • Article
  • Open Access
7 Citations
9,152 Views
23 Pages

Intent Identification by Semantically Analyzing the Search Query

  • Tangina Sultana,
  • Ashis Kumar Mandal,
  • Hasi Saha,
  • Md. Nahid Sultan and
  • Md. Delowar Hossain

22 February 2024

Understanding and analyzing the search intent of a user semantically based on their input query has emerged as an intriguing challenge in recent years. It suffers from small-scale human-labeled training data that produce a very poor hypothesis of rar...

  • Article
  • Open Access
19 Citations
3,502 Views
25 Pages

14 October 2020

The European Commission calls for more small-scale renewable energy producers to actively participate in the energy value chain. In this study, we model an illustrative peer-to-peer (P2P) market with tariffs based on the reservation prices of market...

(This article belongs to the Special Issue Design Optimization of Local Energy Markets)
  • Article
  • Open Access
38 Citations
6,329 Views
16 Pages

24 March 2021

Contemporary manufacturing systems are undergoing a major change promoted by emerging technologies such as Cyber-physical Systems (CPS) or the Internet of Things (IoT). This trend, nowadays widely known by the term “Industry 4.0”, leads to a new kind...

(This article belongs to the Section Systems Engineering)
  • Article
  • Open Access
16 Citations
4,163 Views
16 Pages

Enhancing Environmental Control in Broiler Production: Retrieval-Augmented Generation for Improved Decision-Making with Large Language Models

  • Marcus Vinicius Leite,
  • Jair Minoro Abe,
  • Marcos Leandro Hoffmann Souza and
  • Irenilza de Alencar Nääs

The growing global demand for animal protein, particularly chicken meat, challenges poultry farming to adapt production systems through the adoption of digital technologies. Among the promising advances in artificial intelligence (AI), large language...

(This article belongs to the Special Issue The Future of Artificial Intelligence in Agriculture)
  • Review
  • Open Access
23 Citations
4,513 Views
17 Pages

Radiogenomics in Clear Cell Renal Cell Carcinoma: A Review of the Current Status and Future Directions

  • Sari Khaleel,
  • Andrew Katims,
  • Shivaram Cumarasamy,
  • Shoshana Rosenzweig and ,
  • Kyrollis Attalla,
  • A Ari Hakimi and
  • Reza Mehrazin
  • + 2 authors+ 0 author

22 April 2022

Radiogenomics is a field of translational radiology that aims to associate a disease’s radiologic phenotype with its underlying genotype, thus offering a novel class of non-invasive biomarkers with diagnostic, prognostic, and therapeutic potent...

(This article belongs to the Special Issue Clear Cell Renal Cell Carcinoma 2021–2022)
  • Review
  • Open Access
17 Citations
5,656 Views
16 Pages

Cooperative and connected autonomous vehicles (CCAVs) are considered to be a promising solution for addressing congestion and other operational deficiencies, as part of a holistic future mobility management framework. As a result, a significant numbe...

(This article belongs to the Special Issue Future Mobility and Transport Applications)
  • Article
  • Open Access
1,715 Views
37 Pages

Unbiasing Greek: In-Context Learning Strategies for Gender Bias Identification and Mitigation for Legal Documents and Job Ads

  • Dimitrios Doumanas,
  • Andreas Soularidis,
  • Nikolaos Zafeiropoulos,
  • Stamatis Chatzistamatis and ,
  • George E. Tsekouras,
  • Andreas El Saer,
  • Chrisaphis Nathanailidis and
  • Konstantinos Kotis
  • + 3 authors+ 0 author

2 April 2026

Gender bias embedded in legal and professional texts perpetuates systemic inequality, yet research on bias identification and mitigation remains largely confined to English. Morphologically rich languages such as Greek, where grammatical gender perva...

(This article belongs to the Special Issue Modeling in the Era of Generative AI)
  • Article
  • Open Access
2 Citations
1,278 Views
28 Pages

26 February 2026

Maritime vessel detection in nearshore waters is a fundamental capability for artificial intelligence (AI)-enabled maritime transportation systems, including coastal monitoring, traffic management, and digital maritime services. Although attention me...

(This article belongs to the Special Issue Artificial Intelligence Technology and Application in Marine Science and Engineering)
  • Article
  • Open Access
1,665 Views
19 Pages

5 February 2026

Automatic recognition of endangered animal behavior is crucial for biodiversity conservation and improving animal welfare, yet traditional manual observation remains inefficient and invasive. This work contributes directly to sustainable wildlife man...

  • Proceeding Paper
  • Open Access
308 Views
7 Pages

Multimodal Machine Learning Models Using Zero-Shot Learning to Control Robots

  • Vladimir Kotev,
  • Ivan Ivanov,
  • Kosuke Kakikoshi,
  • Stanislav Georgiev and
  • Ken’ichi Yano

4 August 2026

Substantial growth has been observed in large language models (LLMs), which are increasingly applied across various fields. The integration of vision–language models trained on Internet-scale data into end-to-end robotic control systems to enha...

(This article belongs to the Proceedings of The 15th International Scientific Conference TechSys 2026—Engineering, Technologies and Systems)
  • Article
  • Open Access
2 Citations
2,206 Views
37 Pages

Cascaded Hierarchical Attention with Adaptive Fusion for Visual Grounding in Remote Sensing

  • Huming Zhu,
  • Tianqi Gao,
  • Zhixian Li,
  • Zhipeng Chen and ,
  • Qiuming Li,
  • Kongmiao Miao,
  • Biao Hou and
  • Licheng Jiao
  • + 3 authors+ 0 author

23 August 2025

Visual grounding for remote sensing (RSVG) is the task of localizing the referred object in remote sensing (RS) images by parsing free-form language descriptions. However, RSVG faces the challenge of low detection accuracy due to unbalanced multi-sca...

(This article belongs to the Section AI Remote Sensing)
  • Article
  • Open Access
324 Views
15 Pages

15 September 2026

The present study examined the factor structure, measurement invariance across sex and language, concurrent and discriminant validity and achievement-related criterion validity of the eight-item mathematics self-concept scale from TIMSS 2023 in a sam...

(This article belongs to the Special Issue Advancing Academic Skills in Diverse Learners: Assessment, Theory, and Intervention Strategies)
  • Review
  • Open Access
11 Citations
3,833 Views
29 Pages

A Review of Cross-Modal Image–Text Retrieval in Remote Sensing

  • Lingxin Xu,
  • Luyao Wang,
  • Jinzhi Zhang,
  • Da Ha and
  • Haisu Zhang

11 December 2025

With the emergence of large-scale vision-language pre-training (VLP) models, remote sensing (RS) image–text retrieval is shifting from global representation learning to fine-grained semantic alignment. This review systematically examines two ma...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
664 Views
20 Pages

22 July 2026

Drawing on positive psychology, this study investigated the relationships among language attitudes, student engagement (including its cognitive, emotional, behavioral, and social dimensions), and academic achievement in French. A total of 335 Chinese...

(This article belongs to the Special Issue Academic Performance: Understanding Complex Student Outcomes Through an Integrative Lens)
  • Article
  • Open Access
1 Citations
2,173 Views
22 Pages

23 November 2025

Isolated Sign Language Recognition (ISLR), which focuses on identifying individual signs from sign language videos, presents substantial challenges due to small and ambiguous hand regions, high visual similarity among signs, and large intra-class var...

  • Article
  • Open Access
3 Citations
5,571 Views
22 Pages

RAP-RAG: A Retrieval-Augmented Generation Framework with Adaptive Retrieval Task Planning

  • Xu Ji,
  • Luo Xu,
  • Landi Gu,
  • Junjie Ma and ,
  • Zichao Zhang and
  • Wei Jiang
  • + 1 author+ 0 author

30 October 2025

The Retrieval-Augmented Generation (RAG) framework shows great potential in terms of improving the reasoning and knowledge utilization capabilities of language models. However, most existing RAG systems heavily rely on large language models (LLMs) an...

(This article belongs to the Topic Artificial Intelligence Models, Tools and Applications)

of 4