The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and ot...The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.展开更多
Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame...Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame-work that uses Bidirectional Encoder Representations from Transformers(BERT)for contextual feature extraction and a multiple-window Convolutional Neural Network(CNN)for classification.To identify semantic nuances in email content,BERT embeddings are used,and CNN filters extract discriminative n-gram patterns at various levels of detail,enabling accurate spam identification.The proposed model outperformed Word2Vec-based baselines on a sample of 5728 labelled emails,achieving an accuracy of 98.69%,AUC of 0.9981,F1 Score of 0.9724,and MCC of 0.9639.With a medium kernel size of(6,9)and compact multi-window CNN architectures,it improves performance.Cross-validation illustrates stability and generalization across folds.By balancing high recall with minimal false positives,our method provides a reliable and scalable solution for current spam detection in advanced deep learning.By combining contextual embedding and a neural architecture,this study develops a security analysis method.展开更多
With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard ...With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard expression,which bring serious challenges to traditional classification methods.In order to cope with the above problems,this paper proposes a new ASSC(ALBERT,SVD,Self-Attention and Cross-Entropy)-TextRCNN digital cultural text classification model.Based on the framework of TextRCNN,the Albert pre-training language model is introduced to improve the depth and accuracy of semantic embedding.Combined with the dual attention mechanism,the model’s ability to capture and model potential key information in short texts is strengthened.The Singular Value Decomposition(SVD)was used to replace the traditional Max pooling operation,which effectively reduced the feature loss rate and retained more key semantic information.The cross-entropy loss function was used to optimize the prediction results,making the model more robust in class distribution learning.The experimental results indicate that,in the digital cultural text classification task,as compared to the baseline model,the proposed ASSC-TextRCNN method achieves an 11.85%relative improvement in accuracy and an 11.97%relative increase in the F1 score.Meanwhile,the relative error rate decreases by 53.18%.This achievement not only validates the effectiveness and advanced nature of the proposed approach but also offers a novel technical route and methodological underpinnings for the intelligent analysis and dissemination of digital cultural texts.It holds great significance for promoting the in-depth exploration and value realization of digital culture.展开更多
Silks have various advantages compared with synthetic polymer fibers,such as sustainability,mechanical properties,luster,as well as air and humidity permeability.However,the functionalization of silks has not yet been...Silks have various advantages compared with synthetic polymer fibers,such as sustainability,mechanical properties,luster,as well as air and humidity permeability.However,the functionalization of silks has not yet been fully developed.Functionalization techniques that retain or even improve the sustainability of silk production are required.To this end,a low-cost,effective,and scalable strategy to produce TCSs by integrating yarn-spinning and continuous dip coating technique is developed herein.TCSs with extremely long length(>10 km),high mechanical performance(strength of 443.1 MPa,toughness of 56.0 MJ m−3,comparable with natural cocoon silk),and good interfacial bonding were developed.TCSs can be automatically woven into arbitrary fabrics,which feature super-hydrophobicity as well as rapid and programmable thermochromic responses with good cyclic performance:the response speed reached to one second and remained stable after hundreds of tests.Finally,applications of TCS fabrics in temperature management and dynamic textile displays are demonstrated,confirming their application potential in smart textiles,wearable devices,flexible displays,and human–machine interfaces.Moreover,combination of the fabrication and the demonstrated applications is expected to bridge the gap between lab research and industry and accelerate the commercialization of TCSs.展开更多
High-resolution non-emissive displays based on electrochromic tungsten oxides(WOx)are crucial for future near-eye virtual/augmented reality interactions,given their impressive attributes such as high environmental sta...High-resolution non-emissive displays based on electrochromic tungsten oxides(WOx)are crucial for future near-eye virtual/augmented reality interactions,given their impressive attributes such as high environmental stability,ideal outdoor readability,and low energy consumption.However,the limited intrinsic structure of inorganic materials has presented a significant challenge in achieving precise patterning/pixelation at the micron scale.Here,we successfully developed the direct photolithography for WOx nanoparticles based on in situ photo-induced ligand exchange.This strategy enabled us to achieve ultra-high resolution efficiently(line width<4μm,the best resolution for reported inorganic electrochromic materials).Additionally,the resulting device exhibited impressive electrochromic performance,such as fast response(<1 s at 0 V),high coloration efficiency(119.5 cm^(2) C^(−1)),good optical modulation(55.9%),and durability(>3600 cycles),as well as promising applications in electronic logos,pixelated displays,flexible electronics,etc.The success and advancements presented here are expected to inspire and accelerate research and development(R&D)in high-resolution non-emissive displays and other ultra-fine micro-electronics.展开更多
The display and utilization of historic culture are one of the ways for towns to manifest characteristics, carry forward traditions, and promote competitiveness. As the important part of urban conservation planning, i...The display and utilization of historic culture are one of the ways for towns to manifest characteristics, carry forward traditions, and promote competitiveness. As the important part of urban conservation planning, it is also a hot point in the theoretical research on the historic town protection in China. The "context" of towns refers to the essential connection between human being, natural environment, built environment, and social cultural background in the course of historical development and specific conditions. From the perspective of context, this paper put forward construction strategies for the display and utilization system of historic culture combined with the current situation of historical protection of small towns. Historical changes and contextual elements were analyzed based on the literature research and field investigation of Luojiang District to carry out the design of historical and cultural display structures, tour routes, and presentation modes.展开更多
It is of great scientific significance to construct a 3D dynamic structural color with a special color effect based on the microlens array.However,the problems of imperfect mechanisms and poor color quality need to be...It is of great scientific significance to construct a 3D dynamic structural color with a special color effect based on the microlens array.However,the problems of imperfect mechanisms and poor color quality need to be solved.A method of 3D structural color turning on periodic metasurfaces fabricated by the microlens array and self-assembly technology was proposed in this study.In the experiment,Polydimethylsiloxane(PDMS)flexible film was used as a substrate,and SiO2 microspheres were scraped into grooves of the PDMS film to form 3D photonic crystal structures.By adjusting the number of blade-coated times and microsphere concentrations,high-saturation structural color micropatterns were obtained.These films were then matched with microlens arrays to produce dynamic graphics with iridescent effects.The results showed that by blade-coated two times and SiO2 microsphere concentrations of 50%are the best conditions.This method demonstrates the potential for being widely applied in the anticounterfeiting printing and ultra-high-resolution display.展开更多
Super-fine electrohydrodynamic inkjet(SIJ)printing of perovskite nanocrystal(PNC)colloid ink exhibits significant potential in the fabrication of high-resolution color conversion microstructures arrays for fullcolor m...Super-fine electrohydrodynamic inkjet(SIJ)printing of perovskite nanocrystal(PNC)colloid ink exhibits significant potential in the fabrication of high-resolution color conversion microstructures arrays for fullcolor micro-LED displays.However,the impact of solvent on both the printing process and the morphology of SIJ-printed PNC color conversion microstructures remains underexplored.In this study,we prepared samples of CsPbBr3PNC colloid inks in various solvents and investigated the solvent's impact on SIJ printed PNC microstructures.Our findings reveal that the boiling point of the solvent is crucial to the SIJ printing process of PNC colloid inks.Only does the boiling point of the solvent fall in the optimal range,the regular positioned,micron-scaled,conical PNC microstructures can be successfully printed.Below this optimal range,the ink is unable to be ejected from the nozzle;while above this range,irregular positioned microstructures with nanoscale height and coffee-ring-like morphology are produced.Based on these observations,high-resolution color conversion PNC microstructures were effectively prepared using SIJ printing of PNC colloid ink dispersed in dimethylbenzene solvent.展开更多
Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive te...Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive text data.Their potential integration into clinical settings offers a promising avenue that could transform clinical diagnosis and decision-making processes in the future(Thirunavukarasu et al.,2023).This article aims to provide an in-depth analysis of LLMs’current and potential impact on clinical practices.Their ability to generate differential diagnosis lists underscores their potential as invaluable tools in medical practice and education(Hirosawa et al.,2023;Koga et al.,2023).展开更多
Virtual reality(VR)is regarded as the next-generation display platform for immersive human-computer interaction.To solve the long-existing problem of vergence accommodation conflict in VR,varifocal displays based on t...Virtual reality(VR)is regarded as the next-generation display platform for immersive human-computer interaction.To solve the long-existing problem of vergence accommodation conflict in VR,varifocal displays based on the diffractive Pancharatnam–Berry lens(PBL)are considered as one of the most promising approaches with great compatibility to current display architectures.However,the diffractive nature of PBL leads to serious chromatic aberrations in optical systems,which deteriorates the image quality and discourages its actual usage.展开更多
Aiming at the problems of incomplete characterization of text relations,poor guidance of potential representations,and low quality of model generation in the field of controllable long text generation,this paper propo...Aiming at the problems of incomplete characterization of text relations,poor guidance of potential representations,and low quality of model generation in the field of controllable long text generation,this paper proposes a new GSPT-CVAE model(Graph Structured Processing,Single Vector,and Potential Attention Com-puting Transformer-Based Conditioned Variational Autoencoder model).The model obtains a more comprehensive representation of textual relations by graph-structured processing of the input text,and at the same time obtains a single vector representation by weighted merging of the vector sequences after graph-structured processing to get an effective potential representation.In the process of potential representation guiding text generation,the model adopts a combination of traditional embedding and potential attention calculation to give full play to the guiding role of potential representation for generating text,to improve the controllability and effectiveness of text generation.The experimental results show that the model has excellent representation learning ability and can learn rich and useful textual relationship representations.The model also achieves satisfactory results in the effectiveness and controllability of text generation and can generate long texts that match the given constraints.The ROUGE-1 F1 score of this model is 0.243,the ROUGE-2 F1 score is 0.041,the ROUGE-L F1 score is 0.22,and the PPL-Word score is 34.303,which gives the GSPT-CVAE model a certain advantage over the baseline model.Meanwhile,this paper compares this model with the state-of-the-art generative models T5,GPT-4,Llama2,and so on,and the experimental results show that the GSPT-CVAE model has a certain competitiveness.展开更多
基金supported in part by the Science and Technology Innovation Program of Hunan Province under Grant 2025RC3166the National Natural Science Foundation of China under Grant 62572176the National Key R&D Program of China under Grant 2024YFF0618800.
文摘The rapid advancement of large language models(LLMs)has driven the pervasive adoption of AI-generated content(AIGC),while also raising concerns about misinformation,academic misconduct,biased or harmful content,and other risks.Detecting AI-generated text has thus become essential to safeguard the authenticity and reliability of digital information.This survey reviews recent progress in detection methods,categorizing approaches into passive and active categories based on their reliance on intrinsic textual features or embedded signals.Passive detection is further divided into surface linguistic feature-based and language model-based methods,whereas active detection encompasses watermarking-based and semantic retrieval-based approaches.This taxonomy enables systematic comparison of methodological differences in model dependency,applicability,and robustness.A key challenge for AI-generated text detection is that existing detectors are highly vulnerable to adversarial attacks,particularly paraphrasing,which substantially compromises their effectiveness.Addressing this gap highlights the need for future research on enhancing robustness and cross-domain generalization.By synthesizing current advances and limitations,this survey provides a structured reference for the field and outlines pathways toward more reliable and scalable detection solutions.
基金funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R234)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Spam emails remain one of the most persistent threats to digital communication,necessitating effective detection solutions that safeguard both individuals and organisations.We propose a spam email classification frame-work that uses Bidirectional Encoder Representations from Transformers(BERT)for contextual feature extraction and a multiple-window Convolutional Neural Network(CNN)for classification.To identify semantic nuances in email content,BERT embeddings are used,and CNN filters extract discriminative n-gram patterns at various levels of detail,enabling accurate spam identification.The proposed model outperformed Word2Vec-based baselines on a sample of 5728 labelled emails,achieving an accuracy of 98.69%,AUC of 0.9981,F1 Score of 0.9724,and MCC of 0.9639.With a medium kernel size of(6,9)and compact multi-window CNN architectures,it improves performance.Cross-validation illustrates stability and generalization across folds.By balancing high recall with minimal false positives,our method provides a reliable and scalable solution for current spam detection in advanced deep learning.By combining contextual embedding and a neural architecture,this study develops a security analysis method.
基金funded by China National Innovation and Entrepreneurship Project Fund Innovation Training Program(202410451009).
文摘With the rapid development of digital culture,a large number of cultural texts are presented in the form of digital and network.These texts have significant characteristics such as sparsity,real-time and non-standard expression,which bring serious challenges to traditional classification methods.In order to cope with the above problems,this paper proposes a new ASSC(ALBERT,SVD,Self-Attention and Cross-Entropy)-TextRCNN digital cultural text classification model.Based on the framework of TextRCNN,the Albert pre-training language model is introduced to improve the depth and accuracy of semantic embedding.Combined with the dual attention mechanism,the model’s ability to capture and model potential key information in short texts is strengthened.The Singular Value Decomposition(SVD)was used to replace the traditional Max pooling operation,which effectively reduced the feature loss rate and retained more key semantic information.The cross-entropy loss function was used to optimize the prediction results,making the model more robust in class distribution learning.The experimental results indicate that,in the digital cultural text classification task,as compared to the baseline model,the proposed ASSC-TextRCNN method achieves an 11.85%relative improvement in accuracy and an 11.97%relative increase in the F1 score.Meanwhile,the relative error rate decreases by 53.18%.This achievement not only validates the effectiveness and advanced nature of the proposed approach but also offers a novel technical route and methodological underpinnings for the intelligent analysis and dissemination of digital cultural texts.It holds great significance for promoting the in-depth exploration and value realization of digital culture.
基金supported by the National Natural Science Foundation of China(Nos.51973116,U1832109,21935002,52003156)the Users with Excellence Program of Hefei Science Center CAS(2019HSC-UE003)+1 种基金the starting grant of ShanghaiTech UniversityState Key Laboratory for Modification of Chemical Fibers and Polymer Materials。
文摘Silks have various advantages compared with synthetic polymer fibers,such as sustainability,mechanical properties,luster,as well as air and humidity permeability.However,the functionalization of silks has not yet been fully developed.Functionalization techniques that retain or even improve the sustainability of silk production are required.To this end,a low-cost,effective,and scalable strategy to produce TCSs by integrating yarn-spinning and continuous dip coating technique is developed herein.TCSs with extremely long length(>10 km),high mechanical performance(strength of 443.1 MPa,toughness of 56.0 MJ m−3,comparable with natural cocoon silk),and good interfacial bonding were developed.TCSs can be automatically woven into arbitrary fabrics,which feature super-hydrophobicity as well as rapid and programmable thermochromic responses with good cyclic performance:the response speed reached to one second and remained stable after hundreds of tests.Finally,applications of TCS fabrics in temperature management and dynamic textile displays are demonstrated,confirming their application potential in smart textiles,wearable devices,flexible displays,and human–machine interfaces.Moreover,combination of the fabrication and the demonstrated applications is expected to bridge the gap between lab research and industry and accelerate the commercialization of TCSs.
基金supported by the National Key R&D Program of China(2022YFB3606501,2022YFB3602902)the Key projects of National Natural Science Foundation of China(62234004)+8 种基金the National Natural Science Foundation of China(U23A2092)Pioneer and Leading Goose R&D Program of Zhejiang(2024C01191,2024C01092)Innovation and Entrepreneurship Team of Zhejiang Province(2021R01003)Ningbo Key Technologies R&D Program(2022Z085),Ningbo 3315 Programme(2020A-01-B)YONGJIANG Talent Introduction Programme(2021A-038-B,2021A-159-G)“Innovation Yongjiang 2035”Key R&D Programme(2024Z146)Ningbo JiangBei District public welfare science and technology project(2022C07)the China National Postdoctoral Program for Innovative Talents(grant no.BX20240391)the China Postdoctoral Science Foundation(grant no.2023M743623).
文摘High-resolution non-emissive displays based on electrochromic tungsten oxides(WOx)are crucial for future near-eye virtual/augmented reality interactions,given their impressive attributes such as high environmental stability,ideal outdoor readability,and low energy consumption.However,the limited intrinsic structure of inorganic materials has presented a significant challenge in achieving precise patterning/pixelation at the micron scale.Here,we successfully developed the direct photolithography for WOx nanoparticles based on in situ photo-induced ligand exchange.This strategy enabled us to achieve ultra-high resolution efficiently(line width<4μm,the best resolution for reported inorganic electrochromic materials).Additionally,the resulting device exhibited impressive electrochromic performance,such as fast response(<1 s at 0 V),high coloration efficiency(119.5 cm^(2) C^(−1)),good optical modulation(55.9%),and durability(>3600 cycles),as well as promising applications in electronic logos,pixelated displays,flexible electronics,etc.The success and advancements presented here are expected to inspire and accelerate research and development(R&D)in high-resolution non-emissive displays and other ultra-fine micro-electronics.
文摘The display and utilization of historic culture are one of the ways for towns to manifest characteristics, carry forward traditions, and promote competitiveness. As the important part of urban conservation planning, it is also a hot point in the theoretical research on the historic town protection in China. The "context" of towns refers to the essential connection between human being, natural environment, built environment, and social cultural background in the course of historical development and specific conditions. From the perspective of context, this paper put forward construction strategies for the display and utilization system of historic culture combined with the current situation of historical protection of small towns. Historical changes and contextual elements were analyzed based on the literature research and field investigation of Luojiang District to carry out the design of historical and cultural display structures, tour routes, and presentation modes.
文摘It is of great scientific significance to construct a 3D dynamic structural color with a special color effect based on the microlens array.However,the problems of imperfect mechanisms and poor color quality need to be solved.A method of 3D structural color turning on periodic metasurfaces fabricated by the microlens array and self-assembly technology was proposed in this study.In the experiment,Polydimethylsiloxane(PDMS)flexible film was used as a substrate,and SiO2 microspheres were scraped into grooves of the PDMS film to form 3D photonic crystal structures.By adjusting the number of blade-coated times and microsphere concentrations,high-saturation structural color micropatterns were obtained.These films were then matched with microlens arrays to produce dynamic graphics with iridescent effects.The results showed that by blade-coated two times and SiO2 microsphere concentrations of 50%are the best conditions.This method demonstrates the potential for being widely applied in the anticounterfeiting printing and ultra-high-resolution display.
基金supported by the National Natural Science Foundation of China(No.62374142)Fundamental Research Funds for the Central Universities(Nos.20720220085 and 20720240064)+2 种基金External Cooperation Program of Fujian(No.2022I0004)Major Science and Technology Project of Xiamen in China(No.3502Z20191015)Xiamen Natural Science Foundation Youth Project(No.3502Z202471002)。
文摘Super-fine electrohydrodynamic inkjet(SIJ)printing of perovskite nanocrystal(PNC)colloid ink exhibits significant potential in the fabrication of high-resolution color conversion microstructures arrays for fullcolor micro-LED displays.However,the impact of solvent on both the printing process and the morphology of SIJ-printed PNC color conversion microstructures remains underexplored.In this study,we prepared samples of CsPbBr3PNC colloid inks in various solvents and investigated the solvent's impact on SIJ printed PNC microstructures.Our findings reveal that the boiling point of the solvent is crucial to the SIJ printing process of PNC colloid inks.Only does the boiling point of the solvent fall in the optimal range,the regular positioned,micron-scaled,conical PNC microstructures can be successfully printed.Below this optimal range,the ink is unable to be ejected from the nozzle;while above this range,irregular positioned microstructures with nanoscale height and coffee-ring-like morphology are produced.Based on these observations,high-resolution color conversion PNC microstructures were effectively prepared using SIJ printing of PNC colloid ink dispersed in dimethylbenzene solvent.
文摘Large language models(LLMs),such as ChatGPT developed by OpenAI,represent a significant advancement in artificial intelligence(AI),designed to understand,generate,and interpret human language by analyzing extensive text data.Their potential integration into clinical settings offers a promising avenue that could transform clinical diagnosis and decision-making processes in the future(Thirunavukarasu et al.,2023).This article aims to provide an in-depth analysis of LLMs’current and potential impact on clinical practices.Their ability to generate differential diagnosis lists underscores their potential as invaluable tools in medical practice and education(Hirosawa et al.,2023;Koga et al.,2023).
基金National Natural Science Foundation of China(62405021,U24A20304)Beijing Nova Program(20240484557)。
文摘Virtual reality(VR)is regarded as the next-generation display platform for immersive human-computer interaction.To solve the long-existing problem of vergence accommodation conflict in VR,varifocal displays based on the diffractive Pancharatnam–Berry lens(PBL)are considered as one of the most promising approaches with great compatibility to current display architectures.However,the diffractive nature of PBL leads to serious chromatic aberrations in optical systems,which deteriorates the image quality and discourages its actual usage.
文摘Aiming at the problems of incomplete characterization of text relations,poor guidance of potential representations,and low quality of model generation in the field of controllable long text generation,this paper proposes a new GSPT-CVAE model(Graph Structured Processing,Single Vector,and Potential Attention Com-puting Transformer-Based Conditioned Variational Autoencoder model).The model obtains a more comprehensive representation of textual relations by graph-structured processing of the input text,and at the same time obtains a single vector representation by weighted merging of the vector sequences after graph-structured processing to get an effective potential representation.In the process of potential representation guiding text generation,the model adopts a combination of traditional embedding and potential attention calculation to give full play to the guiding role of potential representation for generating text,to improve the controllability and effectiveness of text generation.The experimental results show that the model has excellent representation learning ability and can learn rich and useful textual relationship representations.The model also achieves satisfactory results in the effectiveness and controllability of text generation and can generate long texts that match the given constraints.The ROUGE-1 F1 score of this model is 0.243,the ROUGE-2 F1 score is 0.041,the ROUGE-L F1 score is 0.22,and the PPL-Word score is 34.303,which gives the GSPT-CVAE model a certain advantage over the baseline model.Meanwhile,this paper compares this model with the state-of-the-art generative models T5,GPT-4,Llama2,and so on,and the experimental results show that the GSPT-CVAE model has a certain competitiveness.
