检索结果-内蒙古大学图书馆

AHFE Virtual Conference on Human Factors and Systems Interaction, 2020

作者： Jadán-Guerrero, Janio Sanchez-Gordon, Sandra Acosta-Vargas, Patricia Alvites-Huamaní, Cleofe Genoveva Nunes, Isabel L. Centro de Investigación en Mecatrónica y Sistemas Interactivos - MIST Universidad Tecnológica Indoamérica Quito Ecuador Department of Informatics and Computer Science Escuela Politécnica Nacional Quito Ecuador Intelligent and Interactive Systems Lab Universidad de Las Américas Quito Ecuador Universidad César Vallejo Lima Peru Faculdade de Ciências e Tecnologia NOVA University of Lisbon Caparica Portugal UNIDEMI Caparica Portugal

ISBN: (纸本)9783030513689

Children with Special Needs may have difficulty understanding the content of a book or associating words and sentences with their meaning. Teachers use the storytelling as a powerful literacy tool which engage children in making connections between academic content and pedagogy. This strategy is also useful to integrate the diversity of the classroom. Increasing or varying the types of materials available to children is another way to make the classroom more inclusive. This paper proposes a new approach for fostering interaction and inclusion development during shared reading. We sought to increase the interactivity of traditional tale books by incorporating elements of technology and storytelling. To develop prototypes we recruited 30 teachers divided into six groups. Each group worked with two challenges: (1) to incorporate technology into a traditional storybook and (2) create an interactive storytelling book for left-handed children. During five work sessions each group developed two proposals: The first proposal was designed with QR codes and the second with NFC tags and augmented reality patterns to facilitate left-handed activities among teachers and children. The proposals were evaluated in the classroom and with experts’ reviews, finding interesting results. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets

arXiv

引用

arXiv 2020年

作者： Choe, Junsuk Oh, Seong Joon Chun, Sanghyuk Lee, Seungho Akata, Zeynep Shim, Hyunjung The Department of Computer Science and Engineering Sogang University Seoul Korea Republic of NAVER AI Lab The School of Integrated Technology Yonsei University Korea Republic of University of Tuebingen Max Planck Institute for Informatics Max Planck Institute for Intelligent Systems Germany

Weakly-supervised object localization (WSOL) has gained popularity over the last years for its promise to train localization models with only image-level labels. Since the seminal WSOL work of class activation mapping (CAM), the field has focused on how to expand the attention regions to cover objects more broadly and localize them better. However, these strategies rely on full localization supervision for validating hyperparameters and model selection, which is in principle prohibited under the WSOL setup. In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set. We observe that, under our protocol, the five most recent WSOL methods have not made a major improvement over the CAM baseline. Moreover, we report that existing WSOL methods have not reached the few-shot learning baseline, where the full-supervision at validation time is used for model training instead. Based on our findings, we discuss some future directions for WSOL. Source code and dataset are available at https://***/clovaai/wsolevaluation. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion Transformer for Remote Sensing Image Classification

arXiv

引用

arXiv 2022年

作者： Roy, Swalpa Kumar Deria, Ankur Hong, Danfeng Rasti, Behnood Plaza, Antonio Chanussot, Jocelyn The Department of Computer Science and Engineering Jalpaiguri Government Engineering College West Bengal Jalpaiguri735102 India The Department of Informatics Technical University of Munich Garching bei München85748 Germany The Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China Helmholtz-Zentrum Dresden-Rossendorf Helmholtz Institute Freiberg for Resource Technology Freiberg09599 Germany The Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politécnica University of Extremadura Cáceres10003 Spain The Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab Grenoble38000 France

Vision transformers (ViTs) have been trending in image classification tasks due to their promising performance when compared to convolutional neural networks (CNNs). As a result, many researchers have tried to incorporate ViTs in hyperspectral image (HSI) classification tasks. To achieve satisfactory performance, close to that of CNNs, transformers need fewer parameters. ViTs and other similar transformers use an external classification (CLS) token which is randomly initialized and often fails to generalize well, whereas other sources of multimodal datasets, such as light detection and ranging (LiDAR) offer the potential to improve these models by means of a CLS. In this paper, we introduce a new multimodal fusion transformer (MFT) network which comprises a multihead cross patch attention (mCrossPA) for HSI land-cover classification. Our mCrossPA utilizes other sources of complementary information in addition to the HSI in the transformer encoder to achieve better generalization. The concept of tokenization is used to generate CLS and HSI patch tokens, helping to learn a distinctive representation in a reduced and hierarchical feature space. Extensive experiments are carried out on widely used benchmark datasets i.e., the University of Houston, Trento, University of Southern Mississippi Gulfpark (MUUFL), and Augsburg. We compare the results of the proposed MFT model with other state-of-the-art transformers, classical CNNs, and conventional classifiers models. The superior performance achieved by the proposed model is due to the use of multihead cross patch attention. The source code will be made available publicly at https://***/AnkurDeria/MFT. © 2022, CC BY.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Multi-view graph learning by joint modeling of consistency and inconsistency

arXiv

引用

arXiv 2020年

作者： Liang, Youwei Huang, Dong Wang, Chang-Dong Yu, Philip S. College of Mathematics and Informatics South China Agricultural University Guangzhou China Tencent Shenzhen China College of Mathematics and Informatics South China Agricultural University Guangzhou China Pazhou Lab Guangzhou China School of Data and Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

—Graph learning has emerged as a promising technique for multi-view clustering due to its ability to learn a unified and robust graph from multiple views. However, existing graph learning methods mostly focus on the multi-view consistency issue, yet often neglect the inconsistency between views, which makes them vulnerable to possibly low-quality or noisy datasets. To overcome this limitation, we propose a new multi-view graph learning framework, which for the first time simultaneously and explicitly models multi-view consistency and inconsistency in a unified objective function, through which the consistent and inconsistent parts of each single-view graph as well as the unified graph that fuses the consistent parts can be iteratively learned. Though optimizing the objective function is NP-hard, we design a highly efficient optimization algorithm that can obtain an approximate solution with linear time complexity in the number of edges in the unified graph. Furthermore, our multi-view graph learning approach can be applied to both similarity graphs and dissimilarity graphs, which lead to two graph fusion-based variants in our framework. Experiments on twelve multi-view datasets have demonstrated the robustness and efficiency of the proposed approach. Copyright © 2020, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Computational Approaches to Explainable Artificial Intelligence: Advances Intheory, Applications and Trends

SSRN

引用

SSRN 2023年

作者： Górriz, Juan Manuel Álvarez-Illán, I. Álvarez-Marquina, A. Arco, J.E. Atzmueller, M. Ballarini, F. Barakova, E. Bologna, G. Bonomini, P. Castellanos-Dominguez, G. Castillo-Barnes, D. Cho, S.B. Contreras, R. Cuadra, J.M. Domínguez, E. Domínguez-Mateos, F. Duro, R.J. Elizondo, D. Fernández-Caballero, A. Fernandez-Jover, E. Formoso, M.A. Gallego-Molina, N.J. Gamazo, J. García González, J. Garcia-Rodriguez, J. Garre, C. Garrigós, J. Gómez-Rodellar, A. Gómez-Vilda, P. Graña, M. Guerrero-Rodriguez, B. Hendrikse, S.C.F. Jimenez-Mesa, C. Jodra-Chuan, M. Julian, V. Kotz, G. Kutt, K. Leming, M. de Lope, J. Macas, B. Marrero-Aguiar, V. Martinez, J.J. Martinez-Murcia, F.J. Martínez-Tomás, R. Mekyska, J. Nalepa, G.J. Novais, P. Orellana, D. Ortiz, A. Palacios-Alonso, D. Palma, J. Pereira, A. Pinacho-Davidson, P. Pinninghoff, M.A. Ponticorvo, M. Psarrou, A. Ramírez, J. Rincón, M. Rodellar-Biarge, V. Rodríguez-Rodríguez, I. Roelofsma, P.H.M.P. Santos, J. Salas-Gonzalez, D. Salcedo-Lagos, P. Segovia, F. Shoeibi, A. Silva, M. Simic, D. Suckling, J. Treur, J. Tsanas, A. Varela, R. Wang, S.H. Wang, W. Zhang, Y.D. Zhu, H. Zhu, Z. Ferrández-Vicente, J.M. SiPBA at Data Science and Computational Intelligence Institute University of Granada Granada Spain University of Granada Granada Spain Dept. of Psychiatry University of Cambridge Cambridge United Kingdom Dept. of Communications Engineering University of Malaga Malaga Spain School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Semantic Information Systems Group Osnabrück University Osnabrück Germany Osnabrück Germany Dept. of Electronics Computer Technology and Projects Universidad Politécnica de Cartagena Cartagena Spain Universitat Politècnica de València València Spain Institute of Applied Computer Science Jagiellonian University Kraków Poland Dept. of Information and Communication Engineering University of Murcia Murcia Spain Dept. of Computer Science and Information Technologies University of A Coruña A Coruña Spain Dept. of Computer Science University of Oviedo Oviedo Spain Buenos Aires Argentina Buenos Aires Argentina Eindhoven University of Technology Eindhoven5612 AZ Netherlands Dept. of Computer Science University of Malaga Malaga Spain De Montfort University Leicester United Kingdom Dept. of Computer Science Faculty of Engineering Universidad de Concepción Concepción Chile Neurocognition and Emotion Research Unit Albacete Research Institute of Informatics University of Castilla-La Mancha Albacete Spain Dept. of Educational Informatics Universidad de Concepción Concepción Chile Madrid Spain Dept. of Humanistic Studies University of Naples Federico II Napoli Italy Escuela Técnica Superior de Ingeniería Informática Universidad Rey Juan Carlos Campus de Móstoles Móstoles Madrid28933 Spain Neuromorphic Speech Processing Lab Center for Biomedical Technology Universidad Politécnica de Madrid Campus de Montegancedo Pozuelo de Alarcón Madrid28223 Spain Biomedical Research Networking Center in Mental Health Instituto de Salud Carlos III Madrid28016 Spain Usher Institute Faculty o

Groundbreaking advances in theoretical and applied Artificial Intelligence (AI). DL algorithms are groundedin non-linear and complex artificial neural systems that progressively extract higher-level features from *** is frequently compared with human-level performance in real-world tasks, such as clinical diagnostics. Itis also a turning point in solving otherwise intractable problems in the design of virtual agents or robotics;orin providing novel insight into disease progress in genomics and Neuroimaging (NI), understanding humanbrain function, the automation of industrial processes based on computer vision, and so on. In this paper, themost relevant advances from the last few years in AI and several applications to neuroscience, neuroimaging,computer vision, and robotics are presented, reviewed and discussed. In this way, we summarize the state-ofthe-art in AI methods, models and applications within a collection of works presented at the 9th InternationalConference on the Interplay between Natural and Artificial Computation (IWINAC). The works presentedin this paper are excellent examples of new scientific discoveries made in laboratories that are successfullytransferred to real-life applications. © 2023, The Authors. All rights reserved.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Knowledge-driven Zero-shot Learning

arXiv

引用

arXiv 2021年

作者： Geng, Yuxia Chen, Jiaoyan Zhuang, Xiang Chen, Zhuo Pan, Jeff Z. Li, Juan Yuan, Zonggang Chen, Huajun College of Computer Science & HIC Zhejiang University 38 Zheda Rd Zhejiang Hangzhou310012 China Knowledge Engine Group AZFT Joint Lab 1818-2 Wenyi West Rd Zhejiang Hangzhou311000 China Department of Computer Science University of Oxford 15 Parks Rd OxfordOX1 3QD United Kingdom School of Informatics The University of Edinburgh 10 Crichton St EdinburghEH8 9AB United Kingdom NAIE Product Department Huawei Technologies Co. Ltd. 101 Software Avenue Nanjing210012 China

External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and attribute, have been widely investigated, but they alone are limited with incomplete semantics. Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge. However, the ZSL community is still in short of standard benchmarks for studying and comparing different external knowledge settings and different KG-based ZSL methods. In this paper, we proposed six resources covering three tasks, i.e., zero-shot image classification (ZS-IMGC), zero-shot relation extraction (ZS-RE), and zero-shot KG completion (ZS-KGC). Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions. We have clearly presented these resources including their construction, statistics, data formats and usage cases w.r.t. different ZSL methods. More importantly, we have conducted a comprehensive benchmarking study, with two general and state-of-the-art methods, two setting-specific methods and one interpretable method. We discussed and compared different ZSL paradigms w.r.t. different external knowledge settings, and found that our resources have great potential for developing more advanced ZSL methods and more solutions for applying KGs for augmenting machine learning. All the resources are available at https://***/China-UK-ZSL/Resources_for_KZSL. © 2021, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

HERMES: a Tool for Mesoscopic Simulation of Advanced Traveller Information Systems

HERMES: a Tool for Mesoscopic Simulation of Advanced Travell...

引用

IEEE International Smart Cities Conference (ISC2)

作者： André Cruz Edgar Carneiro Xavier Fontes Zafeiris Kokkinogenis Rosaldo J. F. Rossetti Artificial Intelligence and Computer Science Lab (LIACC) Department of Informatics Engineering (DEI) Faculty of Engineering University of Porto (FEUP)

ISBN: (数字)9781728108469

ISBN: (纸本)9781728108476

Advanced Traveller Information Systems (ATIS) have seen a steady increase in popularity in the last decades among urban users. By providing travellers with relevant information, these systems have the ability to considerably improve traffic flow, but are limited by their penetration rate among the city's population. In this work we put forward HERMES 1 , a tool to facilitate the evaluation of road networks through simulation with different ATIS and with different levels of information percolation among users. The usefulness of such a tool stems from the quantification of the extent to which an ATIS can improve total travel time and road utilisation by means of experimenting with simulation scenarios. This tool operates at a mesoscopic level, in which single users may be represented independently from each other, nonetheless are rather considered to operate at their macroscopic interactions with the network. We also illustrate example use cases for the tool on the motorway network between the Portuguese cities of Lisbon and Porto.

关键词： Tools Roads Vehicle dynamics Computational modeling Mathematical model Information systems Urban areas

来源：评论

学校读者我要写书评

暂无评论

Biometrics and quality of life of lymphoma patients: A longitudinal mixed-model approach

Biometrics and quality of life of lymphoma patients: A longi...

引用

作者： Oliveira, Alexandra Silva, Eliana Aguiar, Joyce Faria, Brígida Mónica Reis, Luís Paulo Cardoso, Henrique Gonçalves, Joaquim Oliveira e Sá, Jorge Carvalho, Victor Marques, Herlander LIACC - Artificial Intelligence and Computer Science Laboratory Porto Portugal ESS-IPP - Department of Biomathematics Biostatistics and Bioinformatics School of Health Polytechnic Institute of Porto Porto Portugal DEI-FEUP - Department of Informatics Engineering Faculty of Engineering University of Porto Porto Portugal Centro ALGORITMI – University of Minho Guimarães Portugal LITEC - Lab. de Inovação Tecnológica e Engenharia do Conhecimento Porto Portugal 2Ai - Applied Artificial Intelligence Laboratory School of Technology of Polytechnic Institute of Cávado and Ave Barcelos Portugal CINTESIS - Centro de Investigação em Tecnologias e Serviços de Saúde Porto Portugal Centro Hospitalar de Braga Braga Portugal

Knowledge Engineering has become essential in the fields of Medical and Health Care with emphasis for helping citizens to improve their health and quality of life. This includes individual methods and techniques in health-related knowledge acquisition and representation and their application in the construction of intelligent systems capable of using the acquired information to improve the patients' health and/or quality of life. Haemato-oncological diseases can provide significant disability and suffering, with severe symptoms and psychological distress. They can create difficulties in fulfilling professional, family and social roles, affecting an individual's quality of life. Health related quality of life (HRQoL) is a subjective concept but there is also an objective component related to physiological indicators. Some of these physiological indicators can be easily assessed by wearable technology such heart rate variability (HRV). This paper introduces an intelligent system to assess, in real-time, potential HRV indices, that can predict HRQoL in lymphoma patients throughout chemotherapy treatment and to account the individuals' variability. The system is based on wearable technology and intelligent processing of the patients' biometric information to assess some quality of life related parameters. A longitudinal study was conducted among 16 lymphoma patients using this intelligent system. Mixed-effect regression models were performed to investigate predictors for and time effects on HRQoL. There were no significant changes in all HRQoL domains over time. Some quality of life domains revealed similar time trends as HRV indices. These HRV indices also have a significant effect on the domains of quality of life. © 2020 John Wiley & Sons Ltd

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Why is the Winner the Best?

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Compressing Prompts for Efficient Inference of Large Language Models

arXiv

引用

arXiv 2025年

作者： Hu, Jinwu Zhang, Wei Wang, Yufeng Hu, Yu Xiao, Bin Tan, Mingkui Du, Qing School of Software Engineering South China University of Technology China Pazhou Lab Guangzhou China School of Future Technology South China University of Technology Guangzhou China Peng Cheng Laboratory Shenzhen China Department of Health Technology and Informatics Hong Kong Polytechnic University Hong Kong School of Software Engineering South China University of Technology Guangzhou China Department of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

Large Language Models (LLMs) have shown outstanding performance across a variety of tasks, partly due to advanced prompting techniques. However, these techniques often require lengthy prompts, which increase computational costs and can hinder performance because of the limited context windows of LLMs. While prompt compression is a straightforward solution, existing methods confront the challenges of retaining essential information, adapting to context changes, and remaining effective across different tasks. To tackle these issues, we propose a task-agnostic method called Dynamic Compressing Prompts (LLM-DCP). Our method reduces the number of prompt tokens while aiming to preserve the performance as much as possible. We model prompt compression as a Markov Decision Process (MDP), enabling the DCP-Agent to sequentially remove redundant tokens by adapting to dynamic contexts and retaining crucial content. We develop a reward function for training the DCP-Agent that balances the compression rate, the quality of the LLM output, and the retention of key information. This allows for prompt token reduction without needing an external black-box LLM. Inspired by the progressive difficulty adjustment in curriculum learning, we introduce a Hierarchical Prompt Compression (HPC) training strategy that gradually increases the compression difficulty, enabling the DCP-Agent to learn an effective compression method that maintains information integrity. Experiments demonstrate that our method outperforms state-of-the-art techniques, especially at higher compression rates. The code for our approach will be available at https://***/Fhujinwu/DCP. © 2025, CC BY.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：